September 21, 2005
| PhD |
phd
|
| Trust and Reputation |
trust_and_reputation
|
I just finished giving a presentation at the Web Intelligence Conference in Compiegne (France). I tried to push the concept of VoteLinks. The presentation is in S5 (so pure standard XHTML+CSS+JS) and CreativeCommons licenced: Page-reRank: using trusted links to re-rank authority (presentation) with the accompanying paper (pdf). Nothing earth-shaking at all, really. The main (simple) concept was that "Attention != Appreciation", the most linked to page is not necessarily the most appreciated: I might link to gwbush.com in order to criticize it but my link increases its PageRank (something I don't want). At the moment, HTML does not allow to express the reason behind a link, but VoteLinks microformats will allow to add some semantics to linking language. For example, you could say something like
<a href="http://forza-italia.it/" rev="vote-against">berlusconi</a>
<a href="http://romanoprodi.it" rev="vote-abstain">prodi</a>
<a href="http://ivanscalfarotto.info"rev="vote-for">scalfarotto</a>
In the paper I also give evidence of the (intuitive) fact that "Attention!=Appreciation" with a simple experiment on a real, huge community with positive and negative links.
I thought it would be good to have the Web Intelligence community knows about VoteLinks and other microformats. And actually only 1 person (out of a number of people raging from 10 to 30) had heard of VoteLinks before, so the goal of spreading knowledge was accomplished.
And feel free to link to the presentation of course ... hopefully not with a rev="vote-against" link!! ![[winking face]](http://moloko.itc.it/paoloblog/images/smilies/wink.gif){kind=small}
Tomorrow I go to Paris for giving a demo at SonyLabs and then meeting with Alf.
My trip was once more time sponsored by HospitalityClub/CouchSurfing: in Compiegne I was hosted by Jeremy and in Paris by Antonello. Too cool! Try it yourself, you always met great people!
September 18, 2005
Reading How to Make Your Speaking Easier and More Effective:
An old UCLA study of effective presentations analyzed 3 elements (verbal, vocal, visual). Here's what it found was important in establishing credibility/believability:
* Verbal (words you say): 7%.
* Vocal (how you sound when you say them): 38%.
* Visual (how you look when you say them): 55%.
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Semantic web |
semantic_web
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
Some days ago I had to give a presentation for the 2K* symposium, a joint initiative of research groups from different IT institutions, based in Trento and in Genova. The 40 mins presentation was titled "Trust in Recommender Systems: an historical overview and recent developments" (check the source code!). It is heavily based on an old presentation, I just added some slides about microformats, a concept I wanted to convey to the audience.
Anyway, I took the occasion to try to create the presentation in HTML using S5: A Simple Standards-Based Slide Show System developed by Eric Meyer. I think I will create all my future presentation in S5 from now on. The advantages: it "forces" you to keep the slides simple (no unnatural flow of information) and short (however you can have animations, check this slide); it is easy to publish the presentation on the Web, anyone can link to a specific slide, search engines find the information and index them, it is highly standard, evolutionary and small-pieces-loosely-connected-philosophy-like (for exaple it would be possible to create a small piece of javascript code that collect slides from different presentations in some meaningful automatic way to create a new presentation, but the possibilities are endless of course, especially if using the S5 format based on XOXO microformat), I can create the presentation with whatever text editor (perfect if you are in text mode), it does not require the viewer to have some fancy program (openoffice for the freedom lovers, powerpoint for the others) but a browser suffices.
You can find many presentations in S5 format in the microformats wiki; I also liked this presentation of Firefox, with style vulpes-flagrans or with style greenery. Yes, I know the stile I used for my presentation is not that great, if someone with graphical skills would like to create a style for me, it will be very appreciated of course.
For starting playing with S5, I suggest you S5 primer (you need to download HTML code and edit it) or S5present, an open-source web-based slideshow application (you just create an identity there and then use the site for creating the presentation). Guess what? S5 Presents was written in under 10 hours and 500 lines of code using the fantastic Ruby on Rails framework.
[question about English: "take the occasion to"? "take the chance to"? I wanted to say that I used this fact as an opportunity to try the technique. How do you say it in English?]
Tag: s5
September 01, 2005
I'll be at the Web Intelligence 2005 conference from 19 to 22 September and present a paper titled
"Page-reRank: using trusted links to re-rank authority" (pdf). The paper argues, using a real dataset, that a link is not always a vote-for and hence the most linked-to page is not necessarily the "best" page; in short, attention is different than appreciation. However, at the moment, HTML, the current language of the Web, allows to express only attention (just plain links and not the reason for the link) and hence PageRank is only able to detect the pages, people are giving attention to but not the one that are appreciated. The tipical example is a political candidate site under election times: everyone speaks about her but maybe many do it in order to criticize her (yes, think "Bush"). The paper basically recommends VoteLinks as a first step into adding some simple semantics to the "link language". In brief, VoteLinks is one of several microformat open standards. We propose a set of three new values for the rev attribute of the <a> (hyperlink) tag in HTML. The new values are "vote-for" "vote-abstain" or "vote-against", which are mutually exclusive, and represent agreement, abstention or indifference, and disagreement respectively.. So that, with the following HTML code, you can state that you link to a site but you do it for critizing it and search engines, aggregators and rankers should consider this.
<a rev="vote-against" href="http://georgebush.com/" title="miserable failure">Bush</a>.
Anyway I started this post because I'm just happy to say that, just as past AAAI conference, I'll be again hosted by a HospitalityClub.org member: Jérémy, of course I don't know now. The WI05 conference is in Compiegne, a small city close to Paris, but nevertheless there were 4 HC members, I messaged them and in fact one of them, Jeremy, offered to host me, cool! Since I'm going to finish my PhD soon, would you consider hiring a cheap researcher? Cheap in the sense that the university does not have to spend for my wandering around the world, of course See you in Compiegne if you are there or in Paris: on the 23th it is very likely I would be visiting the SonyLabs in Paris.
July 13, 2005
So my presentation of "Controversial Users demand Local Trust Metrics: an Experimental Study on Epinions.com Community" (pdf) went well enough. It was hard to condense in 16 minutes all the background knowledge (epinions.com, trust networks and (local vs global) trust metrics, controversial users) and the experiments I did and the results. I tried but I probably left too much content, this meant I had to run a bit and my English does not allow me to run too fast, I guess I made a lot of English mistakes and I wasn't too clear. I also had another problem: in the early tests, I was not able to connect my GNU/Linux machine to the projector so I had to use the laptop of another speaker, but he didn't have OpenOffice installed (can you imagine that?) and so I run my presentation with Acrobat Reader but all the animations were gone. Well, I guess that it is still a little price you have to pay for choosing freedom (free software as GNU/Linux and OpenOffice).
Anyway, after the presentation, I got some positive feedbacks and some proposals for collaboration so it wasn't too bad.
And lastly, I enjoyed the example about controversial user I gave in the presentation. As you can see in the picture it was George W. Bush. I thought my American audience would have appreciated it and so it was Actually I didn't introduce the slide with too much of a funny story or suspence but it got anyway some laughs. Would you suggest me a good/funny way of introducing this slide, for next presentation? Of course I could have used Berlusconi instead of Bush but I guess I preferred a more aggressive example. Next time, I'll try to joke a little also about myself being a "no global" (not that I like this tag or tags in general) since I critizise global trust metrics and propose Local Trust Metric but this kind of subtle pun requires a great preparation for being effective, funny and understood and I didn't have it. Suggestions in making entertaining presentations are welcome.
As usual the slides are released under a Creative Commons licence: slides in OpenOffice format. Enjoy.
| Folksonomy |
folksonomy
|
| Free software |
free_software
|
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Semantic web |
semantic_web
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
AI Meets Web 2.0: Building The Web of Tomorrow Today by Dr. Jay M. Tenenbaum.
Terrific terrific talk, fascinating. I should have podcasted it because you really missed something (except I have nothing to record audio on, would you consider sending me your old mp3 recorder pen?). I was so excited during the talk that I happened to take a photo of almost any slide. Actually the slides were 94 and I photoed 59 of them! Incredible to me as well.
Anyway, you might want to read the slides (pdf) or maybe you want to have a look at my pictures (possibly as a slideshow).
He introduced all the stuff I enjoy, such as Blogs, RSS, wiki (wikipedia), folksonomies, tags, flickr, Del.icio.us, microformats (aka Lower case semantic web), technorati, pubsub, greasemonkey (bookburro, greasemap) and much more; all tied together in a fascinating, convincing, making-sense manner!
After his presentation, we spoke about my research and he seemed interested. He invited me to visit commerce.net for one month or so and I have to say that I really like the idea. I spoke also with Rohit Khare that is actually working with Tenenbaum and he has a whole bunch of very clever, fascinating, realizable ideas that would really make an impact. They also underline more than once that this kind of architecture/language-of-web2.0 projects should be open source and I totally agree with them and like it.
Actually after the presentation, while I was speaking with Marty and Rohit, there was also Jesse Andrews, the creator of the mind-blowing book burro (actually he got most of the attention, totally deserved by the way). I guess it should be too cool having someone presenting your hack on a conference and then go to meet that person and say "You know the Book Burro extension you presented? Well, I'm the creator of it!". Cool! If you want to see how Jesse looks like, here is a picture of him and wait some more great hacks from him in few days.
In the opening remarks, the chairs ask to stand up to people that were attending the first AAAI conference (25 years ago!). From 6 to 10 standed up, that was a great moment. AAAI conference seems to be like the most important since it is the case that representatives from other 16 difference conferences in AI agreed to send representatives to summarize their results.
Another clever idea is to provide everyone with a Networking Card (see photo): Students have to find 10 faculty for increasing their network and faculty have to find 10 students; the message was "Meet 10 students/faculty new to you and find a common research link". I think this is a perfect excuse to force yourself into bothering that would-be-too-busy-to-talk-to-me professor. Also worth mentioning is the First Annual General Game Playing Competition that would be played here and whose winner will receive a $10,000 prize!
After that we had the Invited talk by Marvin Minsky, one of the founder of AI, you might have read his "Society of Minds" book (1988). He had problems with the computer for at least the first 10 minutes and was making funny remarks about Microsoft's inability to get stuff working. He presented a sort of history of AI. One of his point was that around 1980, AI got "physics envy" and went into heavy reductionism: you subsubsubdivide the big problem of creating "intelligent" entities and you tackle those simpler problems, instead of attacking complexity (I think he called it Panalogy). Then he had problem with the screensaver and the battery of his powerbook.
The slides he created were orrible, with too many words (see an example). He just finished a new book that is available on his homepage for free, it should be The Emotion Machine. I would have preferred him releasing under a Creative Commons licence that makes clear what is legal to do with the book and what not.
Then he started into discussing about "theory of consciousness" and philosophy. I didn't quite get if he was criticizing philosophy as a whole and from now I think he just didn't convey any point at all. At least, later on, he enjoyed the robots.
Summarizing, I was looking for inspiration from his talk and I got none. I guess that it is hard to satisfy all the 800 people in the audience and possibly most of the people liked his talk. Actually there is a post on AAAI blog titled "Minsky disappoints" that critizices the talk (some comments to it confirm, some comments disagree) and another post is more in the middle.
What I like about blogging is that allows you to express an opinion about anything. I mean, I'm critizing Minsky's talk and I'm a totally nobody. But I'm free to do it. Of course my talk will be ages less interesting and my contribution in Science will probably always be less that 1/1000th Minsky's one but I'm free to tell that I didn't like his talk.
July 12, 2005
I was volunteering as a workshops/tutorials floater (in order to get a free registration and a scholarship) and I didn't get a chance to attend too much the workshops. There was a lot of "moving aisles around" in the early morning but then I was pretty free. I spent most of the time at the AAAI blogging platform.
Later this night I'll post about AAAI05 first day: there was the invited talk by Marvin Minsky and a terrific, terrific, terrific, terrific IAAI-05 Invited Talk by Jay M. Tenenbaum "AI Meets Web 2.0: Building The Web of Tomorrow Today". Terrific! I almost photoed every single slide (my camera went dead so I'll post them on Flickr later as well). Terrific talk!
And I'm writing this sitting besides Jesse Andrews, oh yes, that Jesse Andrews, the creator of Book Burro, mindblowing (and business models blowing) application of the century!
July 07, 2005
| PhD |
phd
|
| Trust and Reputation |
trust_and_reputation
|
If you happen to participate in the AAAI 2005 conference (and read this post), pass by to say hello. The paper I'll present is "Controversial Users demand Local Trust Metrics: an Experimental Study on Epinions.com Community" (pdf). Ill be hosted by roder, a (new) friend found via HospitalityClub. Actually I received a lot of offers for hospitality (some via CouchSurfing). And also for hanging around: for example, Violet Law invited me for an Indian party/fundraiser for Indian children on Sunday evening. I guess we can meet there. What a strange, small world?!?
UPDATE: I just received an email from AAAI organizers: AAAI05 has a dedicated blog and an user on Flickr (monitor AAAI05 tag). W00t!
June 15, 2005
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Trust and Reputation |
trust_and_reputation
|
I was invited by Stefano Mizzaro to give a lecture in his course in "Web Information Retrieval". I spoke about "Trust in Recommender Systems: an historical overview and recent developments". It was a lot of fun (at least for me). And I thought I could share the slides with you. They are in OpenOffice .sxi format (it is an open format, so if you program does not read a commonly used open format, you probably better change it). They are released under a Attribution-ShareAlike Creative Commons licence. This means that if you want to use them you just have to give credit to me and re-share your slides under the same licence. If you don't want to re-share your derivative work under the same Creative Commons licence, you are still free, free of not using them. Enjoy.
June 06, 2005
I've just received the Program of the AAAI 2005 Conference (by email) and I post it below for your convenience. I'll present a paper there "Controversial Users demand Local Trust Metrics: an Experimental Study on Epinions.com Community" (pdf). If you are interested or you'll be in Pittsburgh for the conference and want to discuss, please contact me at massa AT itc DOT it.
[ keywords for being indexed: AAAI05, AAAI 05, AAAI2005 , AAAI 2005 ]
AAAI-05 Technical Program Schedule
Sunday, July 10
7:00 - 8:00 PM
AAAI-05 / IAAI-05 Opening Reception
Monday, July 11
8:30 - 9:00 AM
AAAI-05 Welcome and Opening Remarks / Paper Award
Presentations
Manuela Veloso and Subbarao Kambhampati, AAAI-05
Program Cochairs
IAAI-05 Welcome / Deployed Application Award
Announcements
Neil Jacobstein and Bruce Porter, Program Cochairs
AAAI Special Award Presentations
Tom Mitchell, Awards Committee Chair and Ron Brachman,
AAAI President
9:00 - 10:00 AM
AAAI-05 Keynote Address: Marvin Minsky, MIT Media
Laboratory
10:00 - 10:20 AM
Coffee Break
10:20 - 11:20 AM
Technical Paper Session: Machine Learning 1
Discriminative Model Selection for Belief Net
Structures
Yuhong Guo and Russ Greiner
nFOIL: Integrating Naïve Bayes and FOIL
Niels Landwehr, Kristian Kersting, and Luc De Raedt
Online Query Relaxation via Bayesian Causal Structures
Discovery
Ion Muslea and Thomas J. Lee
Technical Paper Session: Planning 1
State Agnostic Planning Graphs and the Application to
Belief-Space Planning
William Cushing and Daniel Bryce
Genome Rearrangement and Planning
Esra Erdem and Elisabeth Tillier
Conformant Planning for Domains with Constraints—A New
Approach
Tran Cao Son, Phan Huy Tu, Michael Gelfond, and A.
Ricardo Morales
Technical Paper Session: Multiagent Systems 1
Supporting Collaborative Activity
Meirav Hadad, Gilad Armon-Kest, Gal A. Kaminka, and
Sarit Kraus
OAR: A Formal Framework for Multi-Agent Negotiation
Jiaying Shen, Ingo Weber, and Victor Lesser
Distributing Coalitional Value Calculations among
Cooperative Agents
Talal Rahwan and Nicholas R. Jennings
Technical Paper Session: Nonmonotonic and Common-Sense
Reasoning
An Axiomatic Account of Formal Argumentation
Martin Caminada and Leila Amgoud
Cumulative Effects of Concurrent Actions on
Numeric-Valued Fluents
Esra Erdem and Alfredo Gabaldon
Practical First-Order Argumentation
Philippe Besnard and Anthony Hunter
Sister Conference Highlights Track
KDD 1: KDD-2004: The Tenth ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining
ICAPS 1: ICAPS-2005: The International Conference on
Automated Planning and Scheduling
UAI 1: UAI-2004: The Twentieth Conference on
Uncertainty in Artificial Intelligence
11:30 AM - 12:30 PM
Technical Paper Session: Constraint Satisfaction 1
Generalized NoGoods in CSPs
George Katsirelos and Fahiem Bacchus
Constrained Decision Diagrams
Kenil C. K. Cheng and Roland H. C. Yap
A Fast Arc Consistency Algorithm for n-ary Constraints
Olivier Lhomme and Jean-Charles Régin
Technical Paper Session: Natural Language Processing 1
Scaling Up Word Sense Disambiguation via Parallel
Texts
Yee Seng Chan and Hwee Tou Ng
Exploiting Subjectivity Classification to Improve
Information Extraction
Ellen Riloff, Janyce Wiebe, and William Phillips
Capturing Expression Using Linguistic Information
Özlem Uzuner and Boris Katz
Technical Paper Session: Multi-Robot Systems
Coordination and Adaptation in Impromptu Teams
Michael Bowling and Peter McCracken
Robust and Self-Repairing Formation Control for Swarms
of Mobile Agents
Jimming Cheng, Winston Cheng, and Radhika Nagpal
Heterogeneous Multirobot Coordination with Spatial and
Temporal Constraints
Mary Koes, Illah Nourbakhsh, and Katia Sycara
Technical Paper Session: Automated Reasoning
Compact Propositional Encodings of First-Order
Theories
Deepak Ramachandran and Eyal Amir
Propositional Fragments for Knowledge Compilation and
Quantified Boolean Formulae
Sylvie Coste-Marquis, Daniel Le Berre, Florian
Letombe, and Pierre Marquis
Recommender Systems: Attack Types and Strategies
Michael P. O’Mahony, Neil J. Hurley, and Guénolé C. M.
Silvestre
Sister Conference Highlights Track
KDD 2: KDD-2004: The Tenth ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining
ICAPS 2: ICAPS-2005: The International Conference on
Automated Planning and Scheduling
UAI 2: UAI-2004: The Twentieth Conference on
Uncertainty in Artificial Intelligence
12:30 - 1:50 PM
Lunch Break
1:50 - 2:50 PM
Technical Paper Session: Vision/Challenge
Tool Use for Autonomous Agents
Robert St. Amant and Alexander B. Wood
A Computational Model of the Cerebral Cortex
Thomas Dean
Samuel Meets Amarel: Automating Value Function
Approximation Using Global State Space Analysis
Sridhar Mahadevan
Technical Paper Session: Temporal Reasoning 1
Temporal Dynamic Controllability Revisited
Paul Morris and Nicola Muscettola
Anytime, Complete Algorithm for Finding Utilitarian
Optimal Solutions to STPPs
Bart Peintner and Martha E. Pollack
Exploiting the Structure of Hierarchical Plans in
Temporal Constraint Propagation
Neil Yorke-Smith
Technical Paper Session: Knowledge Acquisition and
Information Retrieval 1
Searching for Common Sense: Populating Cyc™ from the
Web
Cynthia Matuszek, Michael Witbrock, Robert C. Kahlert,
John Cabral, David Schneider, Purvesh Shah, and Doug
Lenat
Impact of Linguistic Analysis on the Semantic Graph
Coverage and Learning of Document Extracts
Jure Leskovec, Natasa Milic-Frayling, Marko Grobelnik
An Analysis of Knowledge Collected from Volunteer
Contributors
Timothy Chklovski and Yolanda Gil
Technical Paper Session: Human-Computer Interaction
Mathematical Domain Reasoning Tasks in Natural
Language Tutorial Dialog on Proofs
Christoph Benzmüller and Quoc Bao Vo
A Decision Theoretic Model for Stress Recognition and
User Assistance
Wenhui Liao, Weihong Zhang, Zhiwei Zhu, and Qiang Ji
On the Evaluation of Dynamic Critiquing: A Large-Scale
User Study
Kevin McCarthy, Lorraine McGinty, Barry Smyth, and
James Reilly
Sister Conference Highlights Track
CogSci 1: CogSci 2004: The Twenty-Sixth Annual Meeting
of the Cognitive Science Society
ICCBR 1: ICCBR 2003: The Fifth International
Conference on Case-Based Reasoning
KCAP 1: KCAP-2003: The Second International Conference
on Knowledge Capture
3:00 - 4:00 PM
Technical Paper Session: Information Integration
Constraint-Based Entity Matching
Warren Shen, Xin Li, and AnHai Doan
A Constraint Satisfaction Approach to Geospatial
Reasoning
Martin Michalowski and Craig A. Knoblock
Solving Everyday Physical Reasoning Problems by
Analogy Using Sketches
Matthew Klenk, Kenneth D. Forbus, Emmett Tomai,
Hyeonkyeong Kim, and Brian Kyckelhahn
Technical Paper Session: Planning 2
Planning for Stream Processing Systems
Anton Riabov and Zhen Liu
Coordinating Agile Systems through the Model-based
Execution of Temporal Plans
Thomas Léauté and Brian C. Williams
Prottle: A Probabilistic Temporal Planner
Iain Little, Douglas Aberdeen, and Sylvie Thiébaux
Technical Paper Session: Auctions and Market-Based
Systems 1
Profit Sharing Auction
Sandip Sen, Teddy Candale, and Susnata Basak
Approximating Revenue-Maximizing Combinatorial
Auctions
Anton Likhodedov and Tuomas Sandholm
A New Strategy-Proof Greedy-Allocation Combinatorial
Auction Protocol and Its Extension to Open Ascending
Auction Protocol
Takayuki Ito, Makoto Yokoo, Atsushi Iwasaki, and
Shigeo Matsubara
Technical Paper Session: Vision, Music, Speech
Learning Static Object Segmentation from Motion
Segmentation
Michael G. Ross and Leslie Pack Kaelbling
Modeling Form for On-line Following of Musical
Performances
Bryan Pardo and William Birmingham
Spotting Subsequences Matching an HMM Using the
Average Observation Probability Criteria with
Application to Keyword Spotting
Marius Calin Silaghi
Sister Conference Highlights Track
CogSci 2: CogSci 2004: The Twenty-Sixth Annual Meeting
of the Cognitive Science Society
ICCBR 2: ICCBR 2003: The Fifth International
Conference on Case-Based Reasoning
KCAP 2: KCAP-2003: The Second International Conference
on Knowledge Capture
4:00 - 4:20 PM
Coffee Break
4:20 - 5:20 PM
Technical Paper Session: Machine Learning 2
Towards Learning Stochastic Logic Programs from
Proof-Banks
Luc De Raedt, Kristian Kersting, and Sunna Torge
The Regularized EM Algorithm
Haifeng Li, Keshu Zhang, and Tao Jiang
Discovering Domain-Specific Composite Kernels
Thomas Briggs and Tim Oates
Technical Paper Session: Constraint Satisfaction 2
Finding Diverse and Similar Solutions in Constraint
Programming
Emmanuel Hebrard, Brahim Hnich, Barry O’Sullivan, and
Toby Walsh
SAT-Based versus CSP-Based Constraint Weighting for
Satisfiability
Duc Nghia Pham, John Thornton, Abdul Sattar, and
Abdelraouf Ishtaiwi
Generating Hard Satisfiable Formulas by Hiding
Solutions Deceptively
Haixia Jia, Cristopher Moore, and Doug Strain
Technical Paper Session: Multiagent Learning
Efficient No-Regret Multiagent Learning
Bikramjit Banerjee and Jing Peng
Agent-Organized Networks for Multi-Agent Production
and Exchange
Matthew E. Gaston and Marie desJardins
Optimal Efficient Learning Equilibrium: Imperfect
Monitoring in Symmetric Games
Ronen I. Brafman and Moshe Tennenholtz
Technical Paper Session: Markov Decision Processes 1
Planning and Execution with Phase Transitions
Håkan L. S. Younes
Efficient Maximization in Solving POMDPs
Zhengzhu Feng and Shlomo Zilberstein
Error Bounds for Approximate Value Iteration
Rémi Munos
Sister Conference Highlights Track
CP 1: CP 2004: The Tenth International Conference on
Principles and Practice of Constraint Programming
ISWC 1: ISWC-2004: The Third International Semantic
Web Conference
5:30 - 6:30 PM
Invited Talk Session
From Knowledge to Intelligence — Building Blocks and
Applications
Chitta Baral, Arizona State University
Invited Talk (Title TBA)
Amy Greenwald, Brown University
7:30 - 10:00 PM
Fellows Dinner
Tuesday, July 12
8:45 - 9:00 AM
Game Playing Competition Award Presentation
Michael Genesereth, Stanford University
9:00 - 10:00 AM
AAAI Presidential Address
Ronald J. Brachman, Corporation for National Research
Initiatives
10:00 - 10:20 AM
Coffee Break
10:20 - 11:20 AM
Technical Paper Session: Reinforcement Learning 1
Giving Advice about Preferred Actions to Reinforcement
Learners Via Knowledge-Based Kernel Regression
Richard Maclin, Jude Shavlik, Lisa Torrey, Trevor
Walker, and Edward Wild
Improving Action Selection in MDP’s via Knowledge
Transfer
Alexander A. Sherstov and Peter Stone
Reasoning about Intended Actions
Chitta Baral and Michael Gelfond
Technical Paper Session: Search
External-Memory Pattern Databases Using Structured
Duplicate Detection
Rong Zhou and Eric A. Hansen
The Max K-Armed Bandit: A New Model of Exploration
Applied to Search Heuristic Selection
Vincent A. Cicirello and Stephen F. Smith
Large-Scale Parallel Breadth-First Search
Richard E. Korf and Peter Schultze
Technical Paper Session: Constraint Satisfaction 3
SymChaff: A Structure-Aware Satisfiability Solver
Ashish Sabharwal
DC-SSAT: A Divide-and-Conquer Approach to Solving
Stochastic Satisfiability Problems Efficiently
Stephen M. Majercik and Byron Boots
Weighted Super Solutions for Constraint Programs
Alan Holland and Barry O’Sullivan
Technical Paper Session: Logic Programming
Properties of Programs with Monotone and Convex
Constraints
Lengning Liu and Miroslaw Truszczynski
Using SAT and Logic Programming to Design
Polynomial-Time Algorithms for Planning in
Non-Deterministic Domains
Chitta Baral, Thomas Eiter, and Jicheng Zhao
A Theory of Forgetting in Logic Programming
Kewen Wang, Abdul Sattar, and Kaile Su
Sister Conference Highlights Track
KR 1: KR-2004: The Ninth International Conference on
the Principles of Knowledge Representation and
Reasoning
ICML 1: ICML-2004: The Twenty-First International
Conference on Machine Learning
Russell Greiner, University of Alberta
AAMAS 1: AAMAS 2004: The Third International Joint
Conference on Autonomous Agents and Multi Agent
Systems
11:30 AM - 12:30 PM
Technical Paper Session: Machine Learning 3
Spectral Clustering of Biological Sequence Data
William Pentney and Marina Meila
Data-Driven MCMC for Learning and Inference in
Switching Linear Dynamic Systems
Sang Min Oh, James M. Rehg, Tucker Balch, and Frank
Dellaert
Analogical Learning of Visual/Conceptual Relationships
in Sketches
Kenneth D. Forbus, Jeffrey Usher, and Emmett Tomai
Technical Paper Session: Temporal Reasoning 2
Extending Continuous Time Bayesian Networks
Karthik Gopalratnam, Henry Kautz, and Daniel S. Weld
Augmenting Disjunctive Temporal Problems with
Finite-Domain Constraints
Michael D. Moffitt, Bart Peintner, and Martha E.
Pollack
Functional Specification of Probabilistic Process
Models
Avi Pfeffer
Technical Paper Session: Auctions and Market-Based
Systems 2
Solving the Auction-Based Task Allocation Problem in
an Open Environment
David Sarne and Sarit Kraus
Mechanism Design for Single-Value Domains
Moshe Babaioff, Ron Lavi, and Elan Pavlov
Combinatorial Auctions with k-wise Dependent
Valuations
Vincent Conitzer, Tuomas Sandholm, and Paolo Santi
Technical Paper Session: Robotics
Learning CPG Sensory Feedback with Policy Gradient for
Biped Locomotion for a Full-Body Humanoid
Gen Endo, Jun Morimoto, Takamitsu Matsubara, Jun
Nakanishi, and Gordon Cheng
A Relational Representation for Procedural Task
Knowledge
Stephen Hart, Roderic Grupen, and David Jensen
Recovery Planning for Ambiguous Cases in Perceptual
Anchoring
Mathias Broxvall, Silvia Cordeschi, Lars Karlsson, and
Alessandro Saffiotti
Sister Conference Highlights Track
KR 2: KR-2004: The Ninth International Conference on
the Principles of Knowledge Representation and
Reasoning
ICML 2: ICML-2004: The Twenty-First International
Conference on Machine Learning
Russell Greiner, University of Alberta
12:30 - 1:50 PM
Lunch Break
1:50 - 2:50 PM
Invited Talk Session
How Can AI and Robotics Help Us Understand Social
Animal Behavior?
Tucker Balch, Georgia Institute of Technology
May All Your Plans Succeed!
Dana S. Nau, University of Maryland
3:00 - 4:00 PM
Technical Paper Session: Knowledge Representation
Only-Knowing: Taking It Beyond Autoepistemic Reasoning
Gerhard Lakemeyer and Hector J. Levesque
Issues in Reasoning about Interaction Networks in
Cells: Necessity of Event Ordering Knowledge
Nam Tran, Chitta Baral, and Carron Shankland
Prioritized Component Systems
Gerhard Brewka, Ilkka Niemelä, and Miroslaw
Truszczynski
Technical Paper Session: Activity Recognition
Unsupervised Activity Recognition Using Automatically
Mined Common Sense
Danny Wyatt, Matthai Philipose, and Tanzeem Choudhury
Large-Scale Localization from Wireless Signal Strength
Julie Letchner, Dieter Fox, and Anthony LaMarca
Multiple Agent Event Detection and Representation in
Videos
Asaad Hakeem and Mubarak Shah
Technical Paper Session: Game Theory
Approximate Strategic Reasoning through Hierarchical
Reduction of Large Symmetric Games
Michael P. Wellman, Daniel M. Reeves, Kevin M.
Lochner, Shih-Fen Cheng, and Rahul Suri
Coalitional Games in Open Anonymous Environments
Makoto Yokoo, Vincent Conitzer, Tuomas Sandholm, Naoki
Ohta, and Atsushi Iwasaki
Mixed-Integer Programming Methods for Finding Nash
Equilibria
Tuomas Sandholm, Andrew Gilpin, and Vincent Conitzer
Technical Paper Session: Markov Decision Processes 2
Geometric Variance Reduction in Markov Chains.
Application to Value Function and Gradient Estimation
Rémi Munos
Risk-Sensitive Planning with One-Switch Utility
Functions: Value Iteration
Yaxin Liu and Sven Koenig
Networked Distributed POMDPs: New Approaches to
Optimization and Utility Elicitation in Autonomic
Computing
Relu Patrascu, Craig Boutilier, Rajarshi Das, Jeffrey
O. Kephart, Gerald Tesauro, and William E. Walsh
Sister Conference Highlights Track
ACL 1: ACL-2003: The Forty-first Annual Meeting of the
Association for Computational Linguistics
IUI 1: IUI-2005: 2005 International Conference on
Intelligent User Interfaces
SAT 1: SAT 2004: The Seventh International Conference
on Theory and Applications of Satisfiability Testing
4:00 - 4:20 PM
Coffee Break
4:20 - 5:20 PM
Technical Paper Session: Machine Learning 4
Unsupervised and Semi-Supervised Multi-Class Support
Vector Machines
Linli Xu and Dale Schuurmans
Semi-Supervised Sequence Modeling with Syntactic Topic
Models
Wei Li and Andrew McCallum
A Hybrid Generative/Discriminative Approach to
Semi-Supervised Classifier Design
Akinori Fujino, Naonori Ueda, and Kazumi Saito
Technical Paper Session: Case-Based Reasoning
Competence Driven Case-Base Mining
Rong Pan, Qiang Yang, Jeffrey Junfeng Pan, and Lei Li
Complexity-Guided Case Discovery for Case Based
Reasoning
Stewart Massie, Susan Craw, and Nirmalie Wiratunga
Interactive Knowledge Validation and Query Refinement
in CBR
Monica H. Ou, Geoff A. W. West, Mihai Lazarescu, and
Chris Clay
Technical Paper Session: Multiagent Systems 2
A Synthesis of Distributed Constraint Optimization and
POMDPs
Ranjit Nair, Pradeep Varakantham, Milind Tambe, and
Makoto Yokoo
Controversial Users Demand Local Trust Metrics: An
Experimental Study on Epinions.com Community
Paolo Massa and Paolo Avesani
Cooperative Exploration in the Electronic Marketplace
David Sarne and Sarit Kraus
Sister Conference Highlights Track
ACL 2: ACL-2003: The Forty-first Annual Meeting of the
Association for Computational Linguistics
IUI 2: IUI-2005: 2005 International Conference on
Intelligent User Interfaces
SAT 2: SAT 2004: The Seventh International Conference
on Theory and Applications of Satisfiability Testing
5:30 - 6:30 PM
Technical Paper Session: Natural Language Processing 2
Clustering and Classifying Person Names by Origin
Fei Huang, Stephan Vogel, and Alex Waibel
A Probabilistic Classification Approach for Lexical
Textual Entailment
Oren Glickman, Ido Dagan, and Moshe Koppel
Automatic Text Summarization of Newswire: Lessons
Learned from the Document Understanding Conference
Ani Nenkova
Technical Paper Session: Planning 3
Learning Measures of Progress for Planning Domains
SungWook Yoon, Alan Fern, and Robert Givan
Learning Planning Rules in Noisy Stochastic Worlds
Luke S. Zettlemoyer, Hanna M. Pasula, and Leslie Pack
Kaelbling
Lazy Approximation for Solving Continuous
Finite-Horizon MDPs
Lihong Li and Michael L. Littman
Technical Paper Session: Game Playing
Effective Short-Term Opponent Exploitation in
Simplified Poker
Bret Hoehn, Finnegan Southey, Robert C. Holte, and
Valeriy Bulitko
Search versus Knowledge for Solving Life and Death
Problems in Go
Akihiro Kishimoto and Martin Müller
The Semantics of Potential Intentions / 71
Xiaocong Fan and John Yen
6:30 - 9:30 PM
AAAI-05 Poster/Demo Session
Wednesday, July 13
9:00 - 10:00 AM
Invited Talk Session
Representation Policy Iteration: A Unified Framework
for Learning Behavior and Representation
Sridhar Mahadevan, University of Massachusetts,
Amherst
Faceted Metadata in Search Interfaces
Marti Hearst, University of California Berkeley School
of Information Management and Systems
10:00 - 10:20 AM
Coffee Break
10:20 - 11:20 AM
Technical Paper Session: Reinforcement Learning 2
Online Resource Allocation Using Decompositional
Reinforcement Learning
Gerald Tesauro
Planning in Models that Combine Memory with Predictive
Representations of State
Michael R. James and Satinder Singh
Value Functions for RL-Based Behavior Transfer: A
Comparative Study
Matthew E. Taylor, Peter Stone, and Yaxin Liu
Technical Paper Session: Natural Language Processing 3
Cross-Lingual Bootstrapping of Semantic Lexicons: The
Case of FrameNet
Sebastian Padó and Mirella Lapata
Robust Textual Inference Via Learning and Abductive
Reasoning
Rajat Raina, Andrew Y. Ng, and Christopher D. Manning
Learning to Transform Natural to Formal Languages
Rohit J. Kate, Yuk Wah Wong, and Raymond J. Mooney
Technical Paper Session: Preferences
Constraint-Based Preferential Optimization
Steve Prestwich, Francesca Rossi, Kristen Brent
Venable, and Toby Walsh
Optimal Recommendation Sets: Covering Uncertainty over
User Preferences
Robert Price and Paul R. Messinger
Anyone but Him: The Complexity of Precluding an
Alternative
Edith Hemaspaandra, Lane A. Hemaspaandra, and Jörg
Rothe
Technical Paper Session: Discovery and Learning
Representing Conditional Independence Using Decision
Trees
Jiang Su and Harry Zhang
Inducing Hierarchical Process Models in Dynamic
Domains
Ljupco Todorovski, Will Bridewell, Oren Shiran, and
Pat Langley
Incremental Estimation of Discrete Hidden Markov
Models Based on a New Backward Procedure
German Florez-Larrahondo, Susan Bridges, and Eric A.
Hansen
11:30 AM - 12:30 PM
Technical Paper Session: Constraint Satisfaction 4
Performing Bayesian Inference by Weighted Model
Counting
Tian Sang, Paul Beame, and Henry Kautz
Superstabilizing, Fault-Containing Distributed
Combinatorial Optimization
Adrian Petcu, Boi Faltings
Exploiting Temporal Flexibility to Obtain High Quality
Schedules
Nicola Policella, Xiaofang Wang, Stephen F. Smith, and
Angelo Oddi
Technical Paper Session: Search and Planning
Simultaneous Heuristic Search for Conjunctive Subgoals
Lin Zhu and Robert Givan
A Domain-Independent System for Case-Based Task
Decomposition without Domain Theories
Ke Xu and Hector Muñoz-Avila
Cost-Algebraic Heuristic Search
Stefan Edelkamp, Shahid Jabbar, and Alberto Lluch
Lafuente
Technical Paper Session: Data Mining
A Maximum Likelihood Framework for Integrating
Taxonomies
Suju Rajan, Kunal Punera, and Joydeep Ghosh
Enhanced Direct Linear Discriminant Analysis for
Feature Extraction on High Dimensional Data
A. K. Qin, S. Y. M. Shi, P. N. Suganthan, and Marco
Loog
Using Modified Lasso Regression to Learn Large
Undirected Graphs in a Probabilistic Framework
Fan Li and Yiming Yang
Technical Paper Session: Bayesian Networks
Identifying Direct Causal Effects in Linear Models
Jin Tian
A Multifrontal QR Factorization Approach to
Distributed Inference Applied to Multirobot
Localization and Mapping
Frank Dellaert, Alexander Kipp, and Peter Krauthausen
Distribution-Free Learning of Bayesian Network
Structure in Continuous Domains
Dimitris Margaritis
12:30 - 1:50 PM
Lunch Break
1:50 - 2:50 PM
Technical Paper Session: Machine Learning 5
Robust Supervised Learning
J. Andrew Bagnell
Finite Sample Error Bound for Parzen Windows
Peng Zhang, Jing Peng, and Norbert Riedel
Speeding Up Learning in Real-time Search via Automatic
State Abstraction
Vadim Bulitko, Nathan Sturtevant, and Maryia
Kazakevich
Technical Paper Session: Logics
Strong and Uniform Equivalence in Answer-Set
Programming: Characterizations and Complexity Results
for the Non-Ground Case
Thomas Eiter, Michael Fink, Hans Tompits, and Stefan
Woltran
Integrating Description Logics and Action Formalisms:
First Results
Franz Baader, Carsten Lutz, Maja Milicic, Ulrike
Sattler, and Frank Wolter
Diagnosing Terminologies
Stefan Schlobach
Technical Paper Session: Knowledge Acquisition and
Information Retrieval 2
Selection and Ranking of Propositional Formulas for
Large-Scale Service Directories
Ion Constantinescu, Walter Binder, and Boi Faltings
An Analysis of Procedure Learning by Instruction
Jim Blythe
A Learning-Based Term-Weighting Approach for
Information Retrieval
GuangCan Liu, Yong Yu, and Xing Zhu
Technical Paper Session: Diagnosis
On Compiling System Models for Faster and More
Scalable Diagnosis
Jinbo Huang and Adnan Darwiche
Model-Based Monitoring and Diagnosis of Systems with
Software-Extended Behavior
Tsoline Mikaelian, Brian C. Williams, and Martin
Sachenbacher
Diagnosis as Approximate Belief State Enumeration for
Probabilistic Concurrent Constraint Automata
Oliver B. Martin, Brian C. Williams, and Michel D.
Ingham
May 24, 2005
We were required to fill a feedback form, this is more or less what I wrote:
- What did you like best about the workshop?
-- multidisciplinary approach!
-- some of the greatest speakers in the world at the moment are here to give their vision and advice and suggestions. In general, they are very friendly, helpful and interested in our research.
-- we received a lot of stimuli and inputs.
-- the school was free. this was great, otherwise I could have not participated. moreover, the fact that there were scholarships for researchers coming from not-so-rich countries was great since it allowed to have a multi-contries setting, something that is never achievable at conferences.
- What could be improved?
-- there were too few sociologists, especially among students but also among lecturers. Of course it can be the case that sociologists were not aware of the school or that they were not interested. Either cases, it would be better for next year to have more of them.
-- we should have had a list of bibliography to read before coming (not everyone is a physicists! I'm not). Surely we should have at least a list of concepts that lecturers were going to give as granted (such as mean field theory) before coming here.
-- it would have been great to have the slides published on the web before the lectures. Anyway, I understand that most of the times the speakers are going to prepare slides just the night before and this is not a problem. What was not very good is that the slides were not put on the web even after the lecture, this prevented us from reading them and maybe ask questions or fix concepts or check bibliography.
-Other possible improuvements:
-- it would be great to have plugs and wireless access everywhere (also in the lecture rooms).
-- i guess that some private sponsors (showing off their products or having their logo exposed) could be willing to cover part of the expenses.
-- a mailing list (with all the students and lecturers subscribed by default) should be activated some weeks before the school and animated from the beginning by at least one lecturer or organizer. It would be even better to set up a community site with all the photos and profile of participants (built with plone.org or mamboserver.com or some wiki engine).
-- from a technical point of view, I would suggest to give much much more emphasis to *directed weighted* networks, but I guess next year they will be more studied anyway and this will mean that they will be more covered anyway.
May 22, 2005
In the following some comments about the Program of the fifth day.
[some people asked me where they can find the slides, actually all of them should appear on the school page but at the moment only a few are there. I think/hope they will appear in the following days]
[The following comments are probably understandable/useful only to me, since they are quickly written and cover only the main concepts I wanted to carry away for sure from a lecture. I post them here anyway but you've be warned]
20 May 2005
This is a economical/social day. The lecturers are sociologists and economists. Cool! I like diversity of approaches, minds and terminology.
Social networks II
Stan WASSERMAN
Indiana University, Bloomington, U.S.A.
Topics: subgroups, blockmodel.
How to computer social cohesion? Embeddedness (nested subgroups), find significan social subgroups.
n-clique: for every i,j, geodesic_distance(i,j)
TODO: I asked him if there is any measure about controversiality: he suggested to send an email to INSNA. I could ask also about reciprocity, irreciprocity.
LS_set=relative frequency of connections inside a group compared to outside.
TODO: for trust-related topics in SNs, check "Steven Morris" (spreading ...)
TODO: check Concor algorithm. iFj means i is friend of j. iLj means i lives near j. we can define compound relationships as combinations of relationships. for example FLj represents the friends os everyone that lives near j. In this way it is possible to represent relationships about relationships. for example F is included in FF
Networks, public goods and externalities
Fernando VEGA-REDONDO
Universidad de Alicante, Spain
The talk is about economy and networks models.
Local interaction: embedded in social network
Local externalities: payoff depending on neighbours.
What can we model? Technology adoption, Crime and social pathologies, information acquisition, investments in education.
Players have only local information: they are games of incomplete information; in an underlying random (complex) network
Social networks and labor markets
Matthew O. JACKSON
California Institute of Technology, Pasadena, U.S.A.
Very interesting talk.
Application to labor markets. He said "this will be a crush course of Labor economy ... in 15 minutes" cool.
Models of market. In past, they were centralized but in reality local interactions matter: for example, people find jobs not via a single centralized service but via social contacts.
Learning and playing in games
Sanjeev GOYAL
University of Essex, Colchester, U.K.
Networks don't matter always: for example, some properties are invariant of network structure.
Note for myself: star structure is not good, it is possible that everyone will learn the "wrong" action, just if this is adopted by the central node. Well, you can see that the central node can be the media (cnn, murdoch, ...) so this formally demonstrates something that is of course obvious: diversity in information sources is very important for a working society, anyone should be an info spreader and there should be no single big media. "don't hate the media, become the media" (indymedia).
The talk was interesting but a bit too abstract and not too correlated with reality.
Network of firms competition and collaboration
Sanjeev GOYAL
University of Essex, Colchester, U.K.
Network of firms. i-->j means i put dollars in a tie with j. Studying the network we can ask ourself: should the government helps (for national economy) or not (for having a not-poisoned free market) the formation of such ties between local firms?
Recombinant dataset of research & development agreements.
Research and development ties: patent exchanges, joint ventures, ...
Round table
There was an open discussion about the school, what was good, what was improuvable. And also about: what is this "network science"? which perspectives? which features? are we converging to something? It is, as this school demonstrates, a very interdisciplinary field: there are physicists, computer scientists, sociologists, economists, biologists, chemistrists, ...
Laslo Barabasi claimed that many groups around the world want today to offer positions (phd, staff, courses, ...) about this "network science" but the demand and offer are fragmented, he suggested the creation of a community place, maybe a site where submit/request positions [note: i suggest using plone.org (better) or mamboserver.com for the site].
Other points: are we (in this networks science) asking new questions? Is it a new methodology (look at stuff as networks) or it is a new scientific discipline? Is it a new way of looking at old problems? Are we just a "service" for other disciplines (biology, computer science, ...)?
Everyone is sharing the "bright future": the expectation of having more and more positions about this, funds, projects, papers on journals, ... I agree.
Barabasi pointed how that quantum physics was a mess in the beginning, when it was starting, that everyone was saying this is not correct, this is not science, whatever; he sees a similarity with this new emerging "network science". There was a little and very interesting verbal discussion between Stan Wasserman who claimed that this is not a new science, that sociologists have been studying networks in the past 100 years and Barabasi that claimed that the new science was able to find the same pattern in all the networks (biological, internet, web, food, epidemiology, ...) so this is something totally new. [I oversimplifies their positions of course]. Others stated that this is not an evolution of social network analysis: in fact the new science is about finding common properties in all these networks and that sociologists were surely not speaking to biologists suggesting to apply their tools in their networks before the emergence of this new science. Stan was the only sociologist and I think he brought his point but most of the people (want to) think this is a new field. I tend to agree.
PUBLIC LECTURE - The Architecture of Complexity: From the Cell to the World Wide Web
Albert L. BARABASI
University of Notre Dame, Indiana, U.S.A.
This was an open lecture but there was much less people than the ones I was expecting: more or less the double of the normal quantity.
His talk was basic a summary of the achievements of the past 5 years in studying networks. He showed how across different disciplines networks exhibit same patterns (power law, ...)
There will be a NRC (National Research Council) about "network science" who will define how to fund this science in the US, the country that leads research worldwide: if they decide to heavily support and push it, it will be great for all the people in the audience.
In fact there was a lot of expectation for a bright future in his talk and he concluded with a iper-motivational slide (motivational for students and researchers): "... we are still looking for the (...'s) Laws here", where these dots could be one of you! Well, you could feel a lot of excitement in the audience.
Check www.nd.edu/~networks (it will possibly become the community site he was referring to before).
An interesting question was "do you remember chaos theory and all the excitement that was around it some time ago? will network theory be the same?"
GET TO-GETHER DRINK
We had a buffet all together. It was a lot of fun. People present here are very pleasant. I spoke a lot with a cuban girl (at university of Havana). Now the question could be: I'm more interested in learning about Cuba or about networks? Well, not an hard question, no?
In the following some comments about the Program of the forth day.
[The following comments are probably understandable/useful only to me, since they are quickly written and cover only the main concepts I wanted to carry away for sure from a lecture. I post them here anyway but you've be warned]
The structure of biological networks
Reka ALBERT
Pennsylvania State University, University Park, U.S.A.
Fascinating! Have a look at the lecture notes. They were really interesting. the topic was biological networks: 4 kinds of them.
(1) Protein-protein network (for example, of yeast). There is powerlaw in yeast, c.elegans, ...
I was feeling the sense of progress, the sense of "wow, we are riding on the big wave and nobody knows what will happen in few seconds..." It really seems that this is a topic where you can have an impact worldwide, it is so rapidly evolving and so young! You do really build on the discoveries made by other people few weeks before!
(2) methabolical networks
TODO: I need to read "survey models of net formation: stability and efficiency"
what is really interesting of biological networks is that there isn't a single way to map them in networks but many, many, many...
(3) transcription networks
(4) signal transduction pathways:
Are there public databases? some: aligning cells, KIGG, ... Are they already digested? no you need to preprocess them to extract what you want
Feeling: Reka said many times "it will get better", meaning our coverage of data and understanding of genome and biological information. Note for example that the actual coverage of the genome is 10%/20%! and between different datasets (independently collected but representing the same genome, for example yeast) there is an overlapping of only 7%!!! Research is really on the edge!
Epidemic spreading
Alessandro VESPIGNANI
Indiana University, Bloomington, U.S.A.
Great talk again! Indiana seems really a great university.
Open problem: why viruses remain active for years? Theoretically lambda_c=1 for every virus and this is not possible. [I'll try to get the slides...]
keywords for later study: mean field theory, first order parameter, second order parameter, immunization thresholds, use local knowledge for immunization threshold (similar to local trust metrics that use local knowledge: TODO need to think about it)
Physical Internet
Alessandro VESPIGNANI
Indiana University, Bloomington, U.S.A.
Keywords: toMography, since you cannot know all the connection of a router, you have to resort to traceroute-like way of discovering the topology (never thought about it before!). [Parallel thought: routers are like peers in a p2p system. for p2p systems it was reported that users chagne the open source code or reverse engineered the closed source code to change the behaviour of their peers and this produced an instable-nobody-knows-what-is-happening-in-the-complete-netowkr phenomena. Could the same happen for Internet? Well, of course, router administrator are not scruffy hackers that like to play with the code of the routers but at least in principle...]
Small world of internet: mean distance for routers=10, mean distance for ISPs=10.
Assortative and disassortative.
Crovella et al 2002: take a random graph, do traceroute probing and you see a powerlaw, and not the expected POISSON distribution! aaaaarggh! are powerlaw just a flaw in our way of measuring stuff?!? luckily not but pay attention to all those details otherwise you produce non-scientific results! [clauset and Moore, 2004]. Check DIMES (decentralized probing of the internet).
[Note for myself: CRTL+C & CRTL+V is in general illegal in Internet, where everything is copyrighted (all rights reserved) by default].
Social networks
Stan WASSERMAN
Indiana University, Bloomington, U.S.A.
He is a sociologist and statisticians and has a different take on the all matter (for example, he started with some cartoons: "See you in the funny pages" of linton freeman). I like it. Diversity is always good. He showed many friends networks (TODO: find the data). Suggested to subscribe to INSNA mailing list (I already am, in fact I'm here because of an email he sent on this mailing list!). Showed very expressive networks (for example the evolution in time of friendship relationships between child in a school: 1st grader, all connected; 5th grader, boys and girls divided, boys all friends (high degree), girls much much less, some arrows from girls to boys, no arrows from boys to girls .. an image says more that 1000 words sometimes). This networks are called cross-sectional.
He showed some different studies on a network of florentinian families: an edge could represent when a member of family A married a member of family B. An edge could represent a business relationship. He showed different visualizations of the networks and different measures.
Unsuprisely, prominents families are very well connected.
Path: a->b->c
Walk: a->b->c->b
Cycle: a->b->c->a
Strong component= {a,b} a->b and b->a
Weak component= {a,b} a->b (edges in one direction are enough)
Some single values that can be computer for an entire graph:
- Centrality represents roughly the variance of centrality scores.
- degree centrality (homogeneous=1, dishomogeneous=0), closeness centrality, betweenness centrality.
Possible TODO: shows centrality on Italian politicians (it could lead to interest results).
Possible TODO: consider as nodes countries and model their relationships; it should be plenty of data (import/export flows of different products [oil, agriculture, weapons, ...], diplomatics exchanges, people migration flows), with their evolution in time.
Check "Prestige Rank". Cna we model your beliefs based on your networks? ... what about controversiality?
Modelling the dynamics of biological networks
Reka ALBERT
Pennsylvania State University, University Park, U.S.A.
lecture notes
Second part of morning talk
Strategic models of network formation: stability and efficiency
Matthew G. JACKSON
California Institute of Technology, Pasadena, U.S.A.
Game theoretic model of network formation.
Economist approach...
Agents get utility based on their position in the network.
Check slides.
TOTHINK: can pagerank value be considered as a payoff in network?
TODO: check Bala and Goyal (2000) that consider directed networks. What about weighted?
Understanding if society can move away from a local minima nash equilibrium --> if there is forward thinking, it is possible to realize that if I move from corrent state to another (to maximize my instant payoff), it can be the case that also the other players will change their actions and we will all be worst off. Well, it reminded me of one of the last scenes of the movie "War Games".
TODO: check "corominas bosch (2002)"
An external entity can change the payoffs of players: used to model a governments that can tax (subtract Tij) or give subsidies (add Tij). Example: government exiges from telephone companies that they wire also people that are very far away from cities; this produces a model in which, in a sense, telephine companies "tax" people in the cities and "subsidy" people out of cities. This means that regulations external to the "free" market (i.e. laws) are required to move the entire society into a state that is not a nash equilibrium, but that is possibly more equally fair for every single agent.
Can we model the economic market as a small world? Yes, (1) model low cost for forming local connections/links --> high clustering, (2) high value for distant connections --> low diameter, (3) high cost for distant connections --> few distant links; this is essentially the watts-strogats model that creates small world networks.
TOTHINK: collect the dataset of relationships between CEOs of different megacorporations (from theyrule.net, the data should be public) and do something: being in more than 1 board leads to ..., centrality means that ..., ...
I wrote on the notes (but not at all sure where I got this info or if this is correct) that 40.000 new papers are created every single day (in a single discipline), of course nobody can process this new info. Find what NetworkBench is.
TODO: correlation between overlapping and similarity.
Network Visualization
03h00'
Katy BORNER
Indiana University, Bloomington, U.S.A.
3 hours computer session (hand-on) in which we played with different tools and different dataset, very very interesting!
Lecture notes
May 18, 2005
In the following some comments about the Program of the third day.
Sources of data and tools for computational analysis of large-scale bio-molecular networks
Sergei MASLOV
Brookhaven National Laboratory, Upton, U.S.A.
It was raining a lot, I arrived late (the lectures start at 8.30!). The talk seemed very focused on Genes and genoma, stuff that I'm a bit scared about (I guess I perceive them as Pandora's vase)
Search in structured networks
Lada ADAMIC
HP Laboratories, Palo Alto, U.S.A.
Great Talk! Really great! The slides should be on her site. Some keywords: small world, reverse small world, clb nexus, kleinberg, how humans route messages, ...
Statistical mechanics on graphs (I and II)
Riccardo ZECCHINA
the Abdus Salam ICTP, Trieste, Italy
It was fun to see again concepts like P and NP (polynomial and nonpolynomial)and at least in those I have a clear advantage if compared to physicists
Anyway too complicated for me. I skipped the second part.
Community structure
Guido CALDARELLI
Great talk and great speaker! He is writing a book on these concept and the draft is online (note: need to get the URL).
Network Visualization
Computer session.
Katy BORNER
Indiana University, Bloomington, U.S.A.
Hand-on session in which we played a bit with Pajek and IWC (Information Visualization CyberInfrastructure) (the second is open source).
| Blogging |
blogging
|
| Metadata |
metadata
|
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Reviews |
reviews
|
| Semantic web |
semantic_web
|
| Social Software |
social_software
|
Some weeks ago, Tantek was introducing a new microformat hReview.
We are pleased to announce the first public draft (v0.1) of hReview, jointly co-authored by representatives from America Online, CommerceNet Labs, Microsoft, Six Apart, Technorati, and Yahoo!. hReview is an open microformat standard for publishing and indexing distributed reviews on the Web. This standard enables users to contribute, identify, and aggregate review content on their own web sites and blogs as well as on community sites.
I didn't have time yet to dig into it but it is good that they analyzed previous attempts (I was trying to use RVW by Alf Eaton and to keep my list on Allconsuming but I didn't put too much effort into this) and that they ask for Feedback; almost all the links are to Wikipages so you can edit them directly there.
In general I really appreciate the work of Technorati (I also wrote a paper backing their proposal of VoteLinks, submitted to Web Intelligence 2005: "Page-reRank: using trusted links to re-rank authority" (pdf)).
Some other link I'll try to digest later on: jluster on hreview, hreview on technorati, hreview on del.icio.us, organizedshopping on hreview, adriancuthbert suggested to use this_is_an_hreview as common tag (tagspace?).
It would be great to have this format widely adopted so that the amount of decentralized published reviews will become soon huge and I will have a large amount a data for what I'm working on in my PhD: Trust-aware decentralized Recommender Systems. If interested, check my (a bit outdated) PhD proposal at my papers page.
May 17, 2005
Today during the lectures I was falling asleep some times. And you know what was waking me up everytime? The lecturer saying my name! Yes, like in primary schools!
But actually they were not saying "paolo" but "powerlaw". I don't know the phonetic alphabet so I cannot write it but if you try to pronounce it very fast you will see how much they sound the same.
| Peer to peer |
peer_to_peer
|
| PhD |
phd
|
| Trust and Reputation |
trust_and_reputation
|
In the following some comments about the Program of the second day.
Epidemics spreading
Alessandro VESPIGNANI
Indiana University, Bloomington, U.S.A.
Great Lecture! For now, Vespignani is my preferred lecturer. The lecture was very interesting and spoke about how to model deseases and their spreading and how you can immunitize nodes in order to stop the virus (immunize at random is not effective in general, immunizing the hub [nodes with a lot of connections] works very well [you immunize a tiny fraction of the nodes and the virus is stopped] but you have to have a global knowledge of the network that is often not the case. Taking node at random, asking to name a "connection" and immunize that connection works almost as well as immunizing the hubs but you don't need global knowledge: in fact you are probably going to reach the hubs with this strategy.
He was speaking about sex networks, with the (to be expected) note that, when asked explicitly abou the number of sexual connections, men tend to overstimate and women tend to understimate. He said that there are already data on sexual networks from Sweden, US, UK, Zimbabwe, Uganda. Remind for myself: I need to have a look at them and download the data.
[Everyone here is speaking of Mean Field, but I have no idea what this is. Most of the people here are physicists. I had a check on the Mean Field Wikipedia page but I didn't get it too much. I'll have to ask someone, even if this is a bit like asking "what do you mean by 2+2 after 5 years of math".]
Official visit - the Director General of UNESCO Mr. K. MATSUURA
I arrived late and it was boring.
Percolation on networks II
Shlomo HAVLIN
Bar-Ilan University, Ramat-Gan, Israel
Too mathematical for me. Certainly Havlin knows a lot about these things.
Models of scale free graphs
Guido CALDARELLI
Very good speaker as well! The slides were perfect. There was some speaking about fractals, about fractals networks and pseudo-fractal graphs. He spoke about cosing.org where there also some datasets to play with. He made some fun remarks at the end about the sexual networks but I can't remember them. I need to get the slides that were perfect.
Search in random networks
Lada ADAMIC
HP Laboratories, Palo Alto, U.S.A.
I read most of her papers and it was great to see that there is a real person behind the name. Her lecture was interesting and not too hard to follow. Tomorrow she will speak about search on scale-free networks. I need to understand better what are these cutoffs in powerlaw distributions.
Network visualization
Katy BORNER
Indiana Unviersity, Bloomington, U.S.A.
In the next days we will have 3 computer sessions with her in which we will play with datasets and she also asked to bring our datasets. I think it will be fun. I read a paper by her some time ago about activeWorld and visualizations of footprints in a virtual library: very interesting! Anyway this talk was very different from the previoous talk, it was much more graphical, sometime phychological and surely not at all a formulas-dense one!
I will try to get the slides of this as well. Interesting picture of sociogram from a 1934 (!) paper by Moreno. Red and green has swapped meaning in China, compared to Italy.
I suggested her to look at the TrustArt wiki page I somehow maintain, there could be some interesting visualizations she had missed.
Game theory
Fernando VEGA-REDONDO
Universidad de Alicante, Spain
He was great in condensing the all field in one hour and in doing it in a very intriguing way, basically only by examples. Very interesting and at the end he started explained how game theory relates to networks (formation). I took 6 pages of notes. The last line I wrote on my notes is "Economy is the science of greediness and egoism" (you know, all these assumptions about humans being rational, i.e. interested just in maximizing their instantaneous utility not caring for all the rest...)
May 11, 2005
Wikimania 2005: The First International Wikimedia Conference will be held in Frankfurt am Main, Germany from 4 August 2005 to 8 August 2005.
Original research is welcome, but not required. Be bold in your submissions! Wikimania is meant to be both a scientific conference and a social event. (from WikiMania Call4Papers).
I'm thinking about going. By chance, can you host me during these days in Frankfurt?
May 09, 2005
| PhD |
phd
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
Social Capital and Social Networks - Bridging Boundaries conference seems interesting. Moreover there is no registration fee and Junior scholars, graduate students and assistant professors, are invited to apply to attend the conference and receive lodging, meals, and up to $400 in travel expenses. The application deadline was May 5, 2005 (oops). I cannot make it but if you are in US, it is worth checking it.
May 08, 2005
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Trust and Reputation |
trust_and_reputation
|
I'm thinking about writing a book on Trust Metrics, or maybe about Trust Metrics and Recommender Systems. (I need to write my PhD thesis anyway so if I can get it published, this is a plus). Well, a search inside-books on Amazon for "trust metric" reveals this is not a too covered topic. Good. Do you have any suggestion? Publisher, topics, whatever. Anyway being able to search inside (almost) every book in one second is astonishing, sometimes I forget about how astonishing the Web is...
May 06, 2005
| Blogging |
blogging
|
| Folksonomy |
folksonomy
|
| PhD |
phd
|
| Semantic web |
semantic_web
|
I forgot about another paper I wrote: Learning Contextualised Weblog Topics (pdf) will be presented at WWW 2005 2nd Annual Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics in Chiba, Japan, May 10th 2005. My boss was going to WWW2005 for presenting another paper and so we decided to submit our ongoing work to this workshop to get some feedback. We are still working with the system but we should be ready for prime time soon enough ... stay tuned!
[I would have loved to meet Ethan Zuckerman that is the invited speaker at this workshop and whose work on media attention is just delicious. (I even proposed to help him in coding something for monitoring the Italian media world but it's too bad I'm so lazy)]
If you like, check the paper Learning Contextualised Weblog Topics (pdf)
Abstract: In this paper, we examine how a topic-centric view of the Blogosphere can be created. We characterise the problems in aligning similar concepts created by a set of distributed, autonomous users and describe current iniatives to solve the problem. We introduce the Tagsocratic project, a novel initiave to solve the concept alignment problem using techniques derived from research in language acquisition among distributed, autonomous agents.
May 01, 2005
| PhD |
phd
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
I'll be in Trieste at the Abdus Salam ICTP (Unesco funded school) during next 2 weeks (16 - 28 May 2005) for the School and Workshop on Structure and Function of Complex Networks (i was advertising about it time ago and I got accepted). I'm so excited. The list of speakers is simply great (see below) and there are participants from all over the world, in fact "Although the main purpose of the Centre is to help research workers from developing countries, a limited number of students and post-doctoral scientists from developed countries are also welcome to attend.".
If you happen to be there and want to discuss a bit about blogosphere, trust, reputation, social software, social networks, languages, globalization, ... just whatever, please contact me!
Main Topics:
- Characterization and modeling of complex networks;
- Socio-economic networks;
- Technological and communication networks;
- Biological and ecological networks.
Lecturers and Keynote Speakers:
L. Adamic (HP Labs., U.S.A.) R. Albert (Penn. State Univ., U.S.A.) A.-L. Barabasi (Notre Dame, U.S.A.) K. Borner (Indiana Univ., U.S.A.) G. Caldarelli (La Sapienza, Italy) S. Goyal (Essex, U.K.) *M. Granovetter (Stanford Univ., U.S.A.) S. Havlin (Bar-Ilan Univ., Israel) M. O. Jackson (Caltech, U.S.A.) M. Marsili (ICTP, Trieste, Italy) J. Mendes (Porto, Portugal) *M.J.E. Newman (Michigan Uni., U.S.A.) R. Pastor-Satorras (Catalunga, Spain) F. Vega-Redondo (Alicante, Spain) A. Vespignani (Indiana Univ., U.S.A.) * S. Wasserman (Harvard, U.S.A.) R. Zecchina (ICTP, Trieste, Italy)
List of Invited Speakers:
(updated as of January 2005) A. Barrat (Paris-Sud, France) B. Bollobas (Memphis Univ., U.S.A.) S. Bornholdt (Bremen, Germany) R. Burioni (Parma, Italy) A. Calvó (U. Aut. de Barcelona,Spain) R. Cowan (MERIT, Maastricht)) P. De Los Rios (EPFL, Switzerland) A. Diaz-Guilera (Barcelona, Spain) S. Dorogovtsev (Aveiro, Portugal) B. Dutta (Warwick, U.K.) M. Greiner (Siemens, Germany) * B. Huberman (HP Labs., U.S.A.) * S. Jain (University of Delhi, Delhi)) J. Kertesz (Budapest, Hungary) * A. Kirman (CNRS, France) B. Khang (Seoul, Korea) * S. Kirkpatrick (Jerusalem, Israel) * M. Lassig (Cologne, Germany) * S. Leibler (Rockefeller, U.S.A.) * S.S. Manna (Kolkata, India) N. Martinez (Berkeley, U.S.A.) S. Maslov (BNL, U.S.A.) * F. Menczer (Indiana Univ., U.S.A.) * R. Monasson (CNRS, France) * Z. Oltvai (Northwestern Univ., U.S.A.) * K. Sneppen (Niels Bohr Inst., Denmark) T. Snijders (Groningen) Z. Toroczkai (LANL, U.S.A.) * U. Upfal (Brown Univ., U.S.A.) A. Vazquez (Notre Dame, U.S.A.) T. Vicsek (ELTE, Hungary) M. Weigt (Gottingen, Germany) (* to be confirmed )
The Abdus Salam International Centre for Theoretical Physics (ICTP) is organizing a School and Workshop on Structure and Function of Complex Networks, to be held from 16 - 28 May 2005 in Trieste, Italy.
The Organizing Committee will be: A.-L. BARABASI (Notre Dame, U.S.A.), M. MARSILI (ICTP, Trieste, Italy), F. VEGA-REDONDO (Alicante, Spain), A. VESPIGNANI (Indiana University, U.S.A.) and R. ZECCHINA (ICTP, Trieste, Italy).
The Local Organizer will be G. BIANCONI (ICTP, Trieste, Italy).
The finding that many complex systems, from the man-made Internet to the evolutionshaped cell and to the network of social and economical interactions, can be studied and compared on the common ground of network theory, has propelled the field into the attention of the larger scientific community and turned network research into a truly interdisciplinary enterprise.
Measurements performed on a vast number of complex systems have indicated that the networks that underlie them are not random, but have common or specific features that make them suitable for their function. The rapid growth in interest in networks has created the need both for authoritative and pedagogical introductions, lowering the barriers for newcomers and for an exchange of new results and ideas.
This activity is divided into two parts, the first week being a School in which established results in networks will be presented by the Lecturers and the second week, a Workshop to discuss present problems in economical, biological and technological networks. The Organizing Committee promote a call for contributed talks: please send applications, with title and abstract of the proposed talk, only by email to G. Bianconi: gbiancon@ictp.trieste.it no later than 28 February 2005.
| Free software |
free_software
|
| Mozilla |
mozilla
|
| PhD |
phd
|
| Trust and Reputation |
trust_and_reputation
|
For the previously mentioned paper, I created a small Firefox extension called SemanticLinks. The purpose? Showing VoteLinks, rel="nofollow" and information about the linked resource by appending a small icon near the link text (anchor text). SemanticLinks is a simple change of TargetAlert to which I just added a 1%. You can find more information about SemanticLinks and how to install it on the SemanticLinks page. You might also want to see some screenshots.
| PhD |
phd
|
| Trust and Reputation |
trust_and_reputation
|
I uploaded another paper of mine in the papers section. This is still under review for the Web Intelligence 2005 conference and is titled "Page-reRank: using trusted links to re-rank authority" (pdf). Let me know what you think of it, if you like.
Abstract The basis of much of the intelligence on the Web is the hyperlink structure which represents an organising principle based on the human facility to be able to discriminate between relevant and irrelevant material. Second generation search engines like Google make use of this structure to infer the authority of particular web pages. However, the linking mechanism provided by HTML does not allow the author to express different types of links such as positive or negative endorsements of page content. Consequently, algorithms like PageRank produce rankings that do not capture the different intentions of web authors. In this paper, we review some of the initiatives for adding simple semantic extensions to the link mechanism. Using a large real world data set, we demonstrate the different page rankings produced by considering extra semantic information in page links. We conclude that Web intelligence would benefit in adoption of languages that allow authors easily encode simple semantic extensions to their hyperlinks.
April 30, 2005
| Alternative Economy |
alternative_economy
|
| PhD |
phd
|
A paper of mine got accepted for the AAAI conference (see previous post). So I need (1) to go to Pittsburgh on July 9, 2005, (2) to find an accomodation in Pittsburgh from July 9 to July 13, 2005, and (3) to pay for conference registration. Since my institute is not sailing in the gold (this is probably not an English expression, it is an Italian one, "non sta navigando nell'oro" and i liked to write it here), I'm going to ask you if you can help in some way.
I tried to enroll for the Student Scholar and Volunteer Program, some volunteering and being a student can maybe help with (1) and (3), however if you know of any grant for students for travelling from Italy to USA for example, please let me know. About (2), I'm going to check on couchsurfing and on hospitalityclub. However if you live in Pittsburg and are dying of wish to host me (again it is an Italian expression "muori dalla voglia di..."), let me know. I'll be happy to be hosted ... and I promise I'll not use Italianish expressions
UPDATE: i got a suggestion to put here a PayPal button, at first I thought it was a unreasonable suggestion but then "hey maybe it can work". Just 2 notable examples: Kottke becomed a full-time blogger and the authors of the randomly generated paper accepted for conference will give a random-presentation thanks to received donations.
So, before I spend time (sort of money, no?) in setting up a PayPal account, would you donate? ... Never thought I could write something like this. The Web is an expected socially created strange creature, isn't it?
| PhD |
phd
|
| Reviews |
reviews
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
A paper of mine titled "Controversial Users demand Local Trust Metrics: an Experimental Study on Epinions.com Community" (pdf) got accepted for the Twentieth National Conference on Artificial Intelligence (AAAI-05)! Cool! The email I received this morning says "Your paper was one of 148 accepted to AAAI-05, out of 803 submissions. AAAI is a highly selective conference, and you are to be congratulated on your paper's acceptance." This means acceptance rate is 18%. Let me know if you like/dislike the paper or want to discuss its topic a bit. I think controversiality is an important theme and I think there are too many papers that assume that every user/agent has a global goodness value that is the same for everyone (there are some users that are bad for everyone and the goal of the technique is to spot them out). This assumption is unrealistic: just think of Bush or Berlusconi ... some people like them (yeah, I know it's kinda incredible) and some other don't. My paper hopefully provide some evidence about this intuitive phenomena. You might also want to check other papers of mine.
Title: Controversial Users demand Local Trust Metrics: an Experimental Study on Epinions.com Community
Abstract: In today's connected world it is possible and very common to interact with unknown people, whose reliability is unknown. Trust Metrics are a recently proposed technique for answering questions such as "Should I trust this user?". However, most of the current research
assumes that every user has a global quality score and that the goal of the technique is just to predict this correct value. We show, on data from a real and large user community, epinions.com, that such an assumption is not realistic because there is a signi cant
portion of what we call controversial users, users who are trusted and distrusted by many. A global agreement about the trustworthiness value of these users cannot exist. We argue, using computational experiments, that the existence of controversial users (a normal phenomena in societies) demands Local Trust Metrics, techniques able to predict the trustworthiness of an user in a personalized way, depending on the very personal view of the judging user.
April 15, 2005
| PhD |
phd
|
| Reviews |
reviews
|
| Trust and Reputation |
trust_and_reputation
|
Too funny, too sad. SCIgen is an Automatic Computer Science Paper Generator. The program (GPL-licenced and hence Free Software) generates random Computer Science research papers, including graphs, figures, and citations. I was thinking about doing something like it since a lot of time, but wait ... one of the random paper got accepted for a conference!!!
One useful purpose for such a program is to auto-generate submissions to "fake" conferences; that is, conferences with no quality standards, which exist only to make money. A prime example, which you may recognize from spam in your inbox, is SCI/IIIS and its dozens of co-located conferences (for example, check out the gibberish on the WMSCI 2005 website). Using SCIgen to generate submissions for conferences like this gives us pleasure to no end. In fact, one of our papers was accepted to SCI 2005! See Examples for more details.
The accepted paper is Rooter: A Methodology for the Typical Unification of Access Points and Redundancy by Jeremy Stribling, Daniel Aguayo and Maxwell Krohn and the "authors" say We are currently working on the "camera-ready", and received many donations to send us to the conference, so that we can give a randomly-generated talk. Ehi, researcher! You can cite it! After all it is a published paper! Not the crappy stuff you find on blogs! Beware, never cite an online article, only articles published on the old paper at one of the millions of crappy iper-expensive conferences!
And, in case you want to cite a paper of mine, I just created "A Case for Randomized Algorithms" and "Comparing XML and Markov Models" or you can just generate a new paper for me. Writing a paper is now easier than ever!!! I need to click 8 more times on this link and then I can just spend one year on holidays since I already produced a good amount of papers.
[I found the news on BoingBoing, a blog reseachers should cite sometime...]
February 22, 2005
| PhD |
phd
|
| Trust and Reputation |
trust_and_reputation
|
Do you know RoboCup? In the software version, you can program your own football players and then have them competing against the players of someone else. You can use whatever technique and the goal is to score more goals that the competitor. "It is an attempt to foster AI and intelligent robotics research by providing a standard problem where wide range of technologies can be integrated and examined.".
With a similar goal, some researchers are working on a trust competition testbed. The idea? You program your player in the "social game", have it playing against (or with?) the other players and at the end evaluate in some way her performances (how well she reasoned about trusting other players and information in order to reach her objectives). And we can also evaluate how the "society", intended as the ecology of players, evolves (or not) based on the different, local behaviours. Anyway, if you are interested, check the Trust competition Rules (longer pdf version) and Trust competition FAQ. Want to play with the Java code? Unluckly, not yet possible but I guess you might obtain the code if you email them. Release of the testbed distribution is being withheld until July, 2005. At that time, the testbed will be publicly available for experimentation and competition practice.
February 18, 2005
| Blogging |
blogging
|
| PhD |
phd
|
| Reviews |
reviews
|
| Trust and Reputation |
trust_and_reputation
|
Some weeks ago, I received an email from Stefano Mizzaro asking my opinion about his paper Quality Control in Scholarly Publishing: A New Proposal (pdf). In the meantime he came to Trento and we discussed face to face but I want to share here some quick comments I wrote on my wiki about the paper. I liked it, it is very clearly presented, it addresses a real problem and a more and more important one. The math is very clear, sound and makes sense. [Yes he found me because of the blog and not because of my papers and this keeps telling me something]. Read the comments to the paper.
Paper:
Quality Control in Scholarly Publishing: A New Proposal by Stefano Mizzaro
Abstract:
The Internet has fostered a faster, more interactive and effective model of scholarly publishing. However, as the quantity of information available is constantly increasing, its quality is threatened, since the traditional quality control mechanism of peer review is often not used (e.g., in online repositories of preprints, and by people publishing on their Web pages whatever they want).
This paper describes a new kind of electronic scholarly journal, in which the standard submission-review-publication process is replaced by a more sophisticated approach, based on judgments expressed by the readers: in this way, each reader is, potentially, a peer reviewer. New ingredients, not found in similar approaches, are that each reader's judgment is weighted on the basis of the reader's skills as a reviewer, and that readers are encouraged to express correct judgments by a feedback mechanism that estimates their own quality. The new electronic scholarly journal is described in both intuitive and formal ways. Its effectiveness is tested by several laboratory experiments that simulate what might happen if the system were deployed and used.
February 10, 2005
| Free software |
free_software
|
| PhD |
phd
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
I found on SocialPhysics Wiki a very interesting proposal: Eclipse Trust Framework (ETF).
The goal of the ETF Project is to provide an open source framework to support the creation of applications on the Eclipse platform that manage a person’s online context (profile) and identity from the person’s or their agent’s perspective. (Eclipse is one of the most used tool for writing Java code, it is open source and funded mainly by IBM).
The description of the application that SocialPhysics wants to build is hyper-cool as well!
The base app is a downloadable application that helps you manage your identity and interactions with co-workers, customers, business associates and friends.
* Simple, illustrative identity management & social networking app
* Includes UI for viewing and editing your digital identities (profiles)
* Includes a "Microsoft Outlook" plug-in that tracks your email communications and auto-populates a social network
* Includes a “Buddy List” plug-in that allows you to synchronize your profile with others
* Scans email and constructs a graph of relationships with relationship metrics such as connectedness, reciprocity, etc.
* Social network visualization; ability to overlay several networks to determine common relationships and characteristics.
It allows you to create and update distinct personas (we call facets) for each of the various contexts in which you work. These contexts control what aspects of you, your interests, and your relationships will be visible to other individuals, groups, or the entire web. These facet identities are searchable through your network of trusted relationships, enabling you to find friends of friends with common interests, specific expertise, and so on.
The app can be extended with context plug-ins that support new and different "social protocols"--cultural conventions about who can see what about whom, what's measured, what's private, what's shared. Using a community-of-interest plug-in, for example, communities can share insights into "what's hot," and who's working on what, or what's not happening that should be. It might provide community-wide and/or individual metrics of trust, connectedness, centralization and so on.
February 09, 2005
| Alternative Economy |
alternative_economy
|
| PhD |
phd
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
During past week I hosted in my house a russian girl I didn't know before. Why? She asked hospitality through CouchSurfing. I subscribed few months ago to CouchSurfing when I was looking for free hosting in Cyprus. In the meantime I also arranged to find hospitality in Paris. And of course I was very happy to host her (Anna is her name and here is her couchsurfing profile). Feel free to contact me if you pass near Trento, Italy (here is my CouchSurfing profile and it should be easy to find my email address around).
And as an example of how much information you leave behind yourself surfing the web, here you can see a map of places Anna has logged in from.
One evening she asked me to use Internet and I saw she was typing livejournal.com, and yes, she has a blog, though it is in Russian and I cannot understand it.
[CouchSurfing can be interesting also from a research point of view, see much below in the following text]
The Hospitality Club is a web site similar to Couchsurfing, although someone told me that the network is much bigger. And there is also Servas. However Servas was founded in 1949 and it is not a initiative born because of the new possibilities offered by the web. In fact they don't exchange or publish information electronically but you have to ask for the list of a certain country (you want to go) to the local responsible and she will send it to you (by normal mail) the dead-tree list, then you can contact people offering hospitality, Everything is highly certified (the local responsible gives you a sort of Servas Identity Card that certifies you are a good person). Servas is much slower, personally it does not fit at all my requirements, since I often decide to go somewhere less than 20 days before. I tried to use it in US, Belize and Guatemala, always without success. Anyway if you want something slower but more sure and certified, Servas can be your choice.
Ok, so what is CouchSurfing (and HospitalityClub) interesting for?
From a global point of view, I really envision (or dream) a world where everyone is free to move everywhere (no more borders) and, as a first step, a place where everyone that want to travel the world and visit countries would be able to do it hosted by local people and at almost-zero cost. In this way, more and more people will come to know different people (white, black, green, red, muslims, hindis, old, young, ...[add yours]..., just different people, the one we usually fear simply because we don't know them, yes maybe we will able to just laugh when the media or the politicians try to push in our brain the idea that everyone else is a potential terrorist and we should fear her). And moving aroung the world will be possible for everyone and not just rich people as it is now. Surely it is very hard, for example, for people from African Univeristies to participates in International Conferences. And in general for people from not-rich countries to move around the world. That would produce a better world, I'm sure. A world of open houses, open cars, trains and transportation vehicles and .... of open minds.
And from a research point of view? Before hosting Anna, I asked myself questions such as "why should I host this girl I don't know? Will she steal everything I have? Will my house be safe?" (you can complete with the classic paranoid bla bla questions). Why I'm happy to host someone she asks hospitality on the web and not someone that simply stops me on the road saying she has no place to sleep for this night and asking to take advantage of my roof and warm house? Why it is different?
Well, it is just the same question such as: Why I'm happy to buy from someone on ebay and not from someone that stops me on the road saying "i'll ship you a wonderful guitar, just give me now 50 euros"?
Yes I'm going there
What makes people happy to use ebay for sending money to people they DON'T know is the fact that ebay gives "identity" to people, you can see the homepage of someone and you can see her history as a buyer and as a seller, and based on this information you can build and grow trust on her. Yes, Trust was the word I wanted to arrive to.
Basically Couchsurfing (and ebay) gives you additional informatiion based on which you can make decisions. In the real world, would you be happy to host a friend of your father? I think so, and why? Because you father trusts her and you trust your father. As simple as that. So technologies can be used to automate this process (the term "social software" is about this enabling power of ICTs). CouchSurfing collects and shows a lot of "social" information: who surfed with who, who certified who, who referenced who, ...
This goes in the same direction as enabling hitchhiking or car pooling through some trust-facilitator ICTs mechanisms as was writing some time ago in Using social software for good: car pooling. Here the same arguments apply: I might be scared to open my car to a total stranger but, if my mobile tells me that she was already hitchhiked by 1000 other people and nothing bad happened, maybe I will be a little bit more open(minded). And the same if my mobile can tell me that this total stranger was picked up already 3 times by my friend Mary and she was happy with the lift and the conversation.
Actually, some months ago I asked to Couchsurfing founder Casey Fenton if I could get access to the data collected by CS and shown on the site for my research on Trust-aware decentralized recommender systems (PDF). But after a positive reply, I didn't hear from him any news. The social data are very very interesting. I copy and paste from my email to him:
data that are really meaningful for my thesis are the social network data.
in couchsurfing this means:
- friends info (everytime an user explicitly express her "How do you
know
[the information you show for example here
http://couchsurfing.com/linksurf.html?md=2&id=72570 ]
- messages exchanged between users: i'm not interested in the messages
themselves (i assume a message is a measure of interest of sender in
receiver) but only when they occurred and between which users.
- requests to couch surf (that are a special kind of message, very
meaningful in couchsurfing context)
- referrals: who write a referral for whom (with date)
- profile views (when an user visit another user's page)
- contact lists: an user saves another user in her contact list (with date)
- "This is an interesting profile!" clicks: an user votes for another
user as "interesting profile"
- vouch: who vouched for whom (with date)
[date information is very useful as well since with it i can
reconstruct the evolution of the community in time]
all these data can be used to picture different social networks (
involving the same nodes that are users but with different directed
edges between them). it can be interesting to note which maps reflect
eachothers.
Another very interesting piece of information is the location.
There isn't too much research about location-aware recommender systems
and surely few real systems with real users (to the best of my
knowledge). i definetely think that location would be a great
information to have and to study.
In general, if possible, i would like to also have this information
about an user:
#login name (or id if you want to anonimize the dataset).
#country (with longitude and latitute)
#State/Province
#City
#Spoken languages (with levels)
#gender
#age
#Occupation:
#Ethnicity:
#Interests:
#Music, Movies, Books: (particularly important since recommender
systems recommend items such as these ones!)
#Places I have visited: (important for developping a system that
recommends countries to be visited)
#Places I have lived:
#Places I want to go to:
#groups an user belongs to (again good for recommending which group
you might find interesting)
#Couch Available (yes/no/maybe)
#Preferred Gender of surfer:
#Max Surfers Per Night:
#how many photos did the user upload.
#some degree of activity of the user such as (total number of logins,
registration date, logins in the last 30 days, in the last 90 days, ...
a more verbose output would be to log all the dates when an user login
in the system). this information can be useful to conduct studies
considering for example only active users.
# is the user verified? at which level?
# is the user vouched for? (of course i can derive this information
from previous logs)
# is the user ambassador?
# is the user certified? (this means "did he contribute financially?")
I was also asking about detected attempts to spam the network, sybil attacks and the like:
one more question, if i may
what is your experience with SP_ A MM ?
there are people that send spiam (remove the "i") messages to other users?
that write spiam profiles or link to spiam sites?
any fake profile (such as bill gates profile of john kerry profile...)?
any other abuse did you happen to see on couchsurfing?
i'm curious because the other side of social software systems is ...
trying to abuse of them and use them for your "malicious" (depending
on your point of view) interests
(such as selling your book on amazon or attracting visitors to your
spiam page or ...)
Actually I think I'm going to copy also the rest of my email to Casey, maybe you find something interesting in it as well:
Some suggestions:
#have you considered exporting personal and "friends" data of every
user in FOAF format (more info at
http://www.foaf-project.org/ or i can tell you something about it if
you like)?
#it would be great being able to "export" your profile to your blog.
the idea is that you provide some html an user can copy and paste in
her blog and this html "writes" some information from couchsurfing
about her profile such as username, place visited or location or
"Couchsurf in my house" or "surf my couch", the couchsurgging logo and
of course all this information link to couchsurfing.com (it can be
good to spread the existence of your fantastic site!)
this is something similar to "flickr" (see for example caterina blog at
http://caterina.net/ and the photos exported from flickr on her blog
on the right), or allconsuming.net (on the right of my blog
http://moloko.itc.it/paoloblog/ you can see "books i'm reading", they
are "written" by allconsuming using the html i copied there and pasted
it in my blog) and tribe.net. all these services allow you to show
your presence on these communities in your blog/site. [was i clear? if
not, sorry. i can try to be more clear, just let me know]
#there was something about geotagging user pages and let geo-aware
browser and application to see the map of users and browse it but the
main site about it geourl.org just went offline so i'm not sure it is
a meaningful project right now...
#you can even think some integration with flickr, every city can
become a "group photo set" on flickr or couchsurfing users can be
allowed to posts their photos on flickr...just an embryonic idea.
#you can show in the homepage the list of currently logged in users
(such as phpnuke/postnuke-powered portals often do). this could
possibly foster the sense of community.
Last words: Couchsurf the world!
January 26, 2005
| PhD |
phd
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
Over at Terranova, nathan is thinking about trust in games. One of the reasoning lines goes along "more powerful characters can be less trusting of the world around them than the weaker". Interesting, it seems that the weak is obliged to risk by trusting other unknown users while the strong can rely on herself, at least in part.
Anyway, I think virtual worlds are definetely a good playground for studying how social relationships evolve over time. Do you know of any MMORPG that is making available (possibly anonimized) data about characters' interactions? Or do you know of a powerful and open-source framework for quickly creating an appealing online environment in which it would be possible to study those dynamics?
January 25, 2005
| Copyright |
copyright
|
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Trust and Reputation |
trust_and_reputation
|
Interesting NYTimes's article (if you don't want to register, use BugMeNot where you can find shared login and password pairs). Mikhail Gronas discovers that "reviewers gave more five-star reviews than two-star reviews, creating an upward sloping curve". (...) "But the most telling variable is the one star rating. Professor Gronas found that books high on what he called the "controversiality index" are given almost as many one-star as five-star ratings, creating a horseshoe-shaped curve. As it turns out, these books also tend to have high sales."
I've found these patterns analyzing Epinions.com ratings and trust statements (chech the graphs' on the paper (pdf)) but actually I don't think they are that surprising: they seem pretty obvious and I just reported them passing by.
What is really depressing is that Dartmouth is now in the process of patenting software that will be used to determine the "controversiality index".
I'm happy that in Europe we are still fighting against a so-stupid-policy of being able to patent everything, no matter how trivial it is. In this case the controversiality level of a book is something like "if a book received as much 5 ratings as 1 and if the 5 and 1 ratings together are the vast majority of ratings and if the number of received ratings is over a threshold (probably depending on release time), then the book is controversial" (putting it in formula that produces a controversiality value would require 10 minutes at most).
By the way, I'm currently working on the concept of controversiality of users and hopefully a paper is on the way. Controversial users are users who are trusted by many and distrusted by many. (Bush is a good example, but this can happen to highly visible persons in general). The idea is that Local Trust Metrics make sense expecially for highly controversial users (for example, users who are trusted by more than 200 users and DIStrusted by more than 200 users in the community). For those users, it does not make sense to predict a trust value of 0.5 saying that you should trust this user as 0.5 but, instead, to predict you should trust this controversial user as 1 if, for example, all your friends trust her and 0 if all your friends distrust her.
January 22, 2005
| PhD |
phd
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
School and Workshop on Structure and Function of Complex Networks. 16 - 28 May 2005 at Abdus Salam ICTP - Trieste - Italy.
Even if the dealine for the application is already passed, it seems there are still some places. Check the poster (pdf): the invited speakers are just great! Note that "Although the main purpose of the Centre is to help research workers from developing countries, a limited number of students and post-doctoral scientists from developed countries are also welcome to attend." and "There is no registration fee to be paid" (via an email on SOCNET mailinglist of INSNA).
Main Topics:
- Characterization and modeling of complex networks;
- Socio-economic networks;
- Technological and communication networks;
- Biological and ecological networks.
Lecturers and Keynote Speakers:
L. Adamic (HP Labs., U.S.A.) R. Albert (Penn. State Univ., U.S.A.) A.-L. Barabasi (Notre Dame, U.S.A.) K. Borner (Indiana Univ., U.S.A.) G. Caldarelli (La Sapienza, Italy) S. Goyal (Essex, U.K.) *M. Granovetter (Stanford Univ., U.S.A.) S. Havlin (Bar-Ilan Univ., Israel) M. O. Jackson (Caltech, U.S.A.) M. Marsili (ICTP, Trieste, Italy) J. Mendes (Porto, Portugal) *M.J.E. Newman (Michigan Uni., U.S.A.) R. Pastor-Satorras (Catalunga, Spain) F. Vega-Redondo (Alicante, Spain) A. Vespignani (Indiana Univ., U.S.A.) * S. Wasserman (Harvard, U.S.A.) R. Zecchina (ICTP, Trieste, Italy)
List of Invited Speakers:
(updated as of January 2005) A. Barrat (Paris-Sud, France) B. Bollobas (Memphis Univ., U.S.A.) S. Bornholdt (Bremen, Germany) R. Burioni (Parma, Italy) A. Calvó (U. Aut. de Barcelona,Spain) R. Cowan (MERIT, Maastricht)) P. De Los Rios (EPFL, Switzerland) A. Diaz-Guilera (Barcelona, Spain) S. Dorogovtsev (Aveiro, Portugal) B. Dutta (Warwick, U.K.) M. Greiner (Siemens, Germany) * B. Huberman (HP Labs., U.S.A.) * S. Jain (University of Delhi, Delhi)) J. Kertesz (Budapest, Hungary) * A. Kirman (CNRS, France) B. Khang (Seoul, Korea) * S. Kirkpatrick (Jerusalem, Israel) * M. Lassig (Cologne, Germany) * S. Leibler (Rockefeller, U.S.A.) * S.S. Manna (Kolkata, India) N. Martinez (Berkeley, U.S.A.) S. Maslov (BNL, U.S.A.) * F. Menczer (Indiana Univ., U.S.A.) * R. Monasson (CNRS, France) * Z. Oltvai (Northwestern Univ., U.S.A.) * K. Sneppen (Niels Bohr Inst., Denmark) T. Snijders (Groningen) Z. Toroczkai (LANL, U.S.A.) * U. Upfal (Brown Univ., U.S.A.) A. Vazquez (Notre Dame, U.S.A.) T. Vicsek (ELTE, Hungary) M. Weigt (Gottingen, Germany) (* to be confirmed )
The Abdus Salam International Centre for Theoretical Physics (ICTP) is organizing a School and Workshop on Structure and Function of Complex Networks, to be held from 16 - 28 May 2005 in Trieste, Italy.
The Organizing Committee will be: A.-L. BARABASI (Notre Dame, U.S.A.), M. MARSILI (ICTP, Trieste, Italy), F. VEGA-REDONDO (Alicante, Spain), A. VESPIGNANI (Indiana University, U.S.A.) and R. ZECCHINA (ICTP, Trieste, Italy).
The Local Organizer will be G. BIANCONI (ICTP, Trieste, Italy).
The finding that many complex systems, from the man-made Internet to the evolutionshaped cell and to the network of social and economical interactions, can be studied and compared on the common ground of network theory, has propelled the field into the attention of the larger scientific community and turned network research into a truly interdisciplinary enterprise.
Measurements performed on a vast number of complex systems have indicated that the networks that underlie them are not random, but have common or specific features that make them suitable for their function. The rapid growth in interest in networks has created the need both for authoritative and pedagogical introductions, lowering the barriers for newcomers and for an exchange of new results and ideas.
Main Topics:
- Characterization and modeling of complex networks;
- Socio-economic networks;
- Technological and communication networks;
- Biological and ecological networks.
This activity is divided into two parts, the first week being a School in which established results in networks will be presented by the Lecturers and the second week, a Workshop to discuss present problems in economical, biological and technological networks. The Organizing Committee promote a call for contributed talks: please send applications, with title and abstract of the proposed talk, only by email to G. Bianconi: gbiancon@ictp.trieste.it no later than 28 February 2005.
January 16, 2005
| Blogging |
blogging
|
| Metadata |
metadata
|
| PhD |
phd
|
| Social Software |
social_software
|
Some entries ago I was asking if there was somewhere a repository of category-tagged blog posts (for a project I was thinking about with some colleagues on evolution of a shared language). Few days ago, Technorati made a big step in providing it.
It aggregates URLs bookmarked under a certain tag in del.icio.us, photos tagged under the same tag in flickr and ALSO blog posts categorized under the same "tag". Cool! For example, see the page about the tag "peace".
Are there other services that use tags to tag things? Yes, there are. citeUlike lets you tag scientific papers. 43things lets you tag "todo lists" (I didn't play with 43things so I'm not really sure what you tag). For example, see citeUlike page for design "tag" and 43things page for design "tag". Gmail as well allows you to tag received emails but of course (at least for the moment) emails are private and it is not possible to aggregate them. We will investigate "would it be useful?" next time.
Are there more services that allow you to tag things? If you know any, please report them in the comments. I especially think we could really enjoy a songs-tagging site but more about this later.
December 16, 2004
| Copyright |
copyright
|
| PhD |
phd
|
| Trust and Reputation |
trust_and_reputation
|
I would love to attend the Reputation and Trust class of Understanding Online Interaction course by david wiley! It seems he always writes down a short funny story for introducing the weekly topic (and the assignment...). I might borrow the idea if I'll ever teach a class. Unluckly, from Italy, Utah is a bit too far away.
And since he releases the content of his blog under a Creative Commons Attribution - Share Alike license and i do the same for content of this blog, I happily and legally post here all his post, of course giving credit.
Reputation and Trust
B. Have you ever bought anything from Amazon.com?
A. Sure.
B. And you felt comfortable giving them your credit card information because...
A. [incredulously] Because they're Amazon.com!
B. But what about before they were "Amazon.com"?
A. Are you going to talk about walking uphill both ways through deep snow?
B. No, no. That would take us in the wrong direction. [thinking] How about Ebay? Ever buy anything from Ebay?
A. Sure.
B. [with delight] A ha! Caught you in my little trap! You've actually never bought anything *from* Ebay. You've bought things from sellers who used Ebay as a front for their goods.
A. [unimpressed] Fair enough.
B. I understand that you feel comfortable giving your money to Amazon.com, but why are you comfortable giving it to jimbob-roadkill-03?
A. I don't know. Because he's on Ebay??? [looking around for help from other students]
B. It's an interesting phenomnenon, isn't it? Why do we trust people online?
A. Well, with some of them you get to know them really well even though you never meet them face to face.
B. True enough. There are people I feel like I have known forever that I've never seen face to face. We exchange emails, post comments on each others' blogs, read each others' writings, etc. After a while you really do feel like you know them.
A. I guess its the same way you come to trust people in the "real world."
B. Which is... how? How do you know you can trust someone?
A. [with great pride] Well how do you really *know* anything?
B. I think that question leads us down a different path. [thinking again] At what point do you begin trusting someone?
A. After they earn my trust.
B. Okay. Keep going with that. How does someone "earn your trust"?
A. [pauses] Well, I guess through chances to do me wrong. I mean, if someone has an opportunity to really take advantage of me, and they don't, then I start to trust them.
B. What's the difference between that person and another who you might trust with something extremely important to you - say your car, house, or spouse?
A. I guess the person I trust more has had more chances to take advantage of me, but has proven over and over again that he won't.
B. So trust is somehow the product of a person's past interactions with you?
A. Something like that.
B. Would knowing the record of a person's past interactions with *other* people influence your willingness to trust them?
A. You mean like if it turned out they had been stealing from their boss or cheating on their wife or something?
B. Or if they won a Nobel Peace prize, etc.
A. Well, sure. If I've never met a person before, then I don't have that history of interactions with him. I guess finding out how he had interacted with others in the past would be all I had to go on.
B. So knowing a person's reputation can be a substitute for your own personal history of interactions with them?
A. To some extent. I don't think I would trust other people's experience as much as I would trust my own, but it's better than nothing.
B. Let me recast the discussion a little. This all started with the question "would you be comfortable giving your money to someone?" If we change the question to "would you be comfortable taking somone's answer to your question as authoritative?" does it change your answer at all?
A. You mean like in the newsgroups, when people would ask questions and then have them answered by total strangers? So the question is why take their word for it?
B. Sure.
A. Well, if they answer, they must know what they're talking about.
B. [grinning] Think about what you're saying a bit more.
A. I don't know. A lot of times you can get a clue from the words they use. To be simple about it, if they use big words like they know what they're talking about, I guess I think that they probably do.
B. So if a person uses one set of words instead of another (to say *exactly* the same thing) it can come off as more believable?
A. Yea. Actually, I tried this approach in most of the essay questions in history as an undergrad. [general laughter and head nodding around the room]
B. Well, hopefully we can agree that the decision to enter into a financial transaction with a stranger is generally an important one. So is the decision to believe an opinion expressed by a stranger on questions where the accuracy of the answer is important.
A. Granted.
B. So...
A. [cutting in] Ok, I get it! You're going to say something like [clearing throat, and then proceeding in an unnaturally deep voice] 'people don't interact very effectively if they can't trust each other - always watching their backs, etc. So for social software to really let people interact effectively, the software has to deal with the problem of trust.'
B. [bowing to A.] Herr Professor.
[applause from the rest of the class for A.]
[to everyone] You won't be surprised to find out that lots of people have thought about this problem.
A. Or to find that they've written articles about the topic that we have to read...
B. Thanks for the segueway. Try these articles first:
* Kollock's The Production of Trust in Online Markets
* Reputation Systems by Resnick et al.
* Trust Among Strangers in Internet Transactions: Empirical Analysis of eBay's Reputation System, also by Resnick and Zeckhauser
A. So let me guess. Those were the readings for the week, which means that next is...
B. The week's assignment!
Assignment: Synthesis 1
Write a brief piece describing the relationships between cooperation, incentives, reputations, and trust. Focus on connecting the concepts and frameworks in the articles you have read for this class with your own personal experiences. Questions you could answer INCLUDE BUT ARE NOT LIMITED TO: In what manner are reputations and trust incentives in and of themselves? Are reputations any more important in facilitating cooperation online than offline; why or why not? Et cetera.
Don't forget to post your short piece on your blog.
A. [sarcastically] Could you possibly ask a broader question, please?
B. That's part of the point. I want to give you a fairly broad license to show that you're really doing some thinking. Synthesize. Connect your experiences to what you've read.
A. Ok. I'm off to think.
December 07, 2004
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
Paul Resnick is researching on "ride sharing services that dynamically match riders with rides". Read the very interesting and clear SocioTechnical Support for Ride Sharing scenario document. The idea is to make car pooling easier using ICT. If your interests contain trust, recommender systems and making the earth a better place, you should definitely read the paper. Maybe I'll try to put up a project and submit to the local government, there was a car pooling project in Trento but it seems dead. Contact me if you are interested! [My impression is that often research does not produce useful and real benefit for society, this is a case in which we can put our brain activity for creating something useful and that can make a difference].
Excerpt from SocioTechnical Support for Ride Sharing by Paul Resnick, Associate Professor University of Michigan, School of Information
I. Intro/Overview
In America, there is tremendous unused transportation capacity in the form of unoccupied seats in private vehicles. Not only would filling some of those seats reduce smog, congestion, and fuel consumption, but it also could create opportunities for increasing local social capital. The major barriers to ride sharing include coordination of routes and schedules, safety risks, social discomfort with sharing what are currently private spaces, and an imbalance of costs and benefits among the affected parties. Despite these barriers, ride sharing does occur, both in the form of recurring carpools and van pools. According to one estimate, more than twice as many people in America share a ride to work in a private vehicle as use public transportation to get there [ref.] In a few cities, there is even instant ride sharing among strangers. Emerging changes in the technology infrastructure of our society may soon make it possible to reduce some of the barriers that have limited the appeal of instant ride sharing. The first change is the widespread deployment of cell phones and other mobile communication devices, with the prospect that they soon be integrated with a position-sensing infrastructure. The second is advances in computational power that may allow for dynamic route matching of drivers and riders. The third is the development of reputation systems on the Internet for maintaining trust among strangers. Research is need on how to leverage these developments to create a SocioTechnical infrastructure for instant ride sharing.
II. Scenario
Janine is new to instant ride-sharing. She is twenty-five and single. She s trying to save money and besides, it s such a hassle to park at the hospital where she works as a research assistant administering clinical trials. She sometimes stays late at work, so she never joined a carpool, but she s decided to try the new Ann Arbor/Ypsilanti instant carpool system. She was a little worried about taking rides with strange men, so she set her profile to only accept rides from women, or from men who had a history of giving at least 10 previous rides without any complaints from riders. She logs onto the website and enters her address and her destination address. She finds that if she walks only to the corner of her current block, she ll have to wait an average of 15 minutes to get a ride, and sometimes much longer, but if she walks two blocks further, to a main street, she can usually get a ride within 3 minutes. She decides to walk the two blocks. This first morning, she s kind of curious about what kind of person picks up riders, so she checks off the box that indicates she s willing to converse the driver.
She s still a little nervous, so she doesn t allow any of her personal information (name, address, or interests) to be revealed to the driver. She s talked to other people who found people to play music with or got a ride all the way home by revealing some information, but she s decided to wait and see how the whole system works first. As she walks out the door, she calls the number she had pre-programmed into her cell phone. The system tracks her progress as she walks to the main street and tells her that a blue Toyota Matrix is just three blocks away and that she should hold up her instant ride-share sign. It gives her a code that she s supposed to say to the driver, and a code that the driver is supposed to say to her. Sure enough, the car pulls up. The driver is a forty-something woman, smartly dressed with a white lab coat on the passenger seat. They exchange codes and Janine jumps in the back. The driver asks Janine what she does at the hospital and soon they discover that the driver and Janine s boss are good friends from way back, and tells a humorous story about her boss when he was first getting started in medical research. As they pull into a choice parking space at the hospital parking lot, reserved for multiple occupant vehicles, the driver smiles and says, You saved me 5 minutes driving around and around in this lot. Thanks. Maybe I ll take you again some time, but my schedule s very irregular so I m not sure when. Thank you! says Janine as they walk off in different directions. As she walks away, she calls the ride sharing system again from her cell phone and presses a button to indicate that she arrived safely, that she would be happy to ride with that driver again, and that she recommends her to other passengers.
[/end of Excerpt]
November 11, 2004
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Semantic web |
semantic_web
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
[I'll write something about my trip in Israel later on, as time permits]
I just found on HubLog an online service I was really waiting for: CiteULike (a prototype service to manage your personal library of academic papers). When you are logged in and visiting a page related to a paper, you can post that paper to your online library using a bookmarklet. In doing so, you can also specify tags, a list of keywords you'd like to associate with this article (a la del.icio.us and flickr) and optional notes. The service is very similar to del.icio.us (simple, tag-powered and social), but precisely tailored for academic papers. You can also see all the papers tagged under a certain tag (for example networks). Cool!
You can see your library (see mine), and see which other users are reading the papers you find interesting. The about page tells you what is coming soon. I think that "exporting those data in semantic web formats" and "opening the API" can be interesting additions to the list. This would be great for creating Trust-aware Recommender System tailored for researchers.
The big problem I see is that only papers in (PubMed, HubMed, JSTOR, arxiv, IngentaConnect) can be added for now. Most of the papers I'm interested in are not stored on those online repositories.
I wish it would be possible to add Citeseer (I'm involved in a project whose goal is to relaunch citeseer), eprints archives and Springler (see my last paper page on Springler for a typical paper page).
I'd like also to be able to keep some blog posts (not published) in my online library and papers that researchers keep in their homepages: using the URL as key for the "paper" could do the work but this will make the site just as del.icio.us is now and I think this is not the goal of the online service. Maybe it would make sense to introduce two levels of papers: certified (by some recognized authority such as PubMed) and uncertified (such as my papers I keep on my blog) but I'm not sure this is a good idea.
October 26, 2004
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Trust and Reputation |
trust_and_reputation
|
I'm at Coopis 2004 right now (in Agia Napa, Cyprus) and next week I'll move to Jerusalem in order to meet Zvi and other people of the Multiagent Systems Research Group of the Hebrew University of Jerusalem. I'll be back in my office on November 9.
I was hoping to do a lot of work during the coopis conference but the wireless network is not working very well and so expect few or no blogging at all.
I almost forgot to say that I'm presenting "Trust-aware Collaborative Filtering for Recommender Systems" (find it under papers section). Check it out if you are interested in Recommender Systems and Trust.
October 18, 2004
| Blogging |
blogging
|
| PhD |
phd
|
| Semantic web |
semantic_web
|
Some colleagues of mine are working on "how people can reach a shared common dictionary/language to denote concepts" (or at least understand each other still using their keywords). See Advertising games. We want to test ideas using real data from the blogosphere. The idea is to detect when 2 bloggers are posting about the same concept/topic but use different names to tag it (the post's category). For example, I use "trust and reputation", someone else uses "reputation" but we may speak about the same concept.
The questions:
- There is an aggregated repository of posts with categories?
- If not, Have you any idea about how can I collect this information?
Requirement:
- posts must have a category associated (livejournal and blogger don't let do this, while MovableType and Wordpress yes).
Some ongoing web search about the topic we're doing can be found at this wiki page, and this too. Thanks for help!
October 13, 2004
| Free software |
free_software
|
| Peer to peer |
peer_to_peer
|
| PhD |
phd
|
| Social Software |
social_software
|
Citeseer is less useful today than how it was 2 years ago. It seems they stop the crawling looking for papers. [I have a project about adding "web of trust" to citeseer so that every user can express a degree of interest in another users' kept bibliography) but it seems I never have the time to seriously start it.] Anyway this post is to cite 2 interesting related projects: LionShare and Eprints ... (read below for links and details)
LionShare P2P project (see the search screenshot on the wiki) allows people to stop thinking P2P is illegal by default. It is Java Open Source code.
"LionShare P2P project is an innovative effort to facilitate legitimate file-sharing among individuals and educational institutions around the world. By using Peer to Peer (P2P) technology and incorporating features such as authentication, directory servers, and owner controlled sharing of files, LionShare promises secure file-sharing capabilities for the easy exchange of image collections, video archives, large data collections, and other types of academic information. In addition to authenticated file-sharing capabilities, the developing LionShare technology will also provide users with resources for organizing, storing, and retrieving digital files."
(found via the iper-interesting Italian WikiLab).
The other interesting project is more mature and is called Eprints.org - Self-Archiving and Open Access (OA) Eprint Archives. The software is called GNU eprints and it is of course free software. At present, there are 141 known archives running EPrints software worldwide. It is a sort of p2p network where peers are libraries (also University libraries) that certificates that the papers they host are real papers from their scholars. I think that every single researcher can have her own instance of the peer but I think noone is doing it. [Anyway I didn't investigate too much the project and I could be wrong]. My University Library is one of the 141, good! Among the softwares, there is CiteBase whose goal is, I guess, very similar to citeseer.
You can also admire some powerlaws (are they ubiquitous?) in these graphs (Java applets).
The different eprints peers keep them up to date using the Open Archives Initiative Protocol for Metadata Harvesting.
Ok, I must admit I didn't check the projects in great details so if you do it (or even install them!), leave some comments (if you feel like). Thanks!
September 25, 2004
| FOAF |
foaf
|
| PhD |
phd
|
| Semantic web |
semantic_web
|
| Trust and Reputation |
trust_and_reputation
|
The FOAF workshop in Galway was almost 20 days ago, so the following report is a little bit late. Hope it can be useful at least as an historical memory.
It was fantastic to meet in flesh many people I just learnt to appreciate through their blogs. Many of the papers were very interesting. I especially like the idea of "Semantic cookies" (you keep your profile [as FOAF file] in a cookie and, with some trick, you give access to every site to it, sites can read it and give you a personalized experience) and "Bootstrapping the FOAF-Web: An Experiment in Social Network Mining" by Peter Mika (the idea is to use Google to infer social relationships among people). And there was also my paper of course. The presentation was so and so, I think I try to put too many concepts for a 15 minutes presentation. The only stuff I liked was the subtitle I wrote at the last second on the first slide: "Moleskiing: Climbing the peaks of FOAF".
Almost half of the workshop was devoted to very interesting Breakout sessions.
They were self-organized sessions where everyone was free to propose a topic (writing it on a paper on the wall) and everyone was free to join any of the sessions. Then based on numbers of interested people and topics, organizers were trying to suggest putting together different sections, if needed. I guess the FOAF and Trust session should have interested me but I was busy creating the presentation I gave the day after and I miss almost all of it (remind for myself: always prepare slides before conference!)
Something very thrilling was also the use of a backchannel on IRC. Many of us were connected to the Internet via WiFI during the talks and we were discussing, adding links, writing down talks. It was the first time I was using such a parallel real-time discussion space and I seldom use IRC so it was a strange and new experience for me, a kind of "augmented" conference. And it was strange to read the IRC log of what was said on the IRC channel #foaf during my presentation.
I met very interesting people. In the picture you can see Marc Canter moving around data, as he said). Marc is really as you could imagine him from his blog, he really says "coolio" and the lesson he gave us about how to deal with venture capitalists in front of a Guinness (picture) was very insightful, or maybe it was just the Guinness I don't remember... his foafnet effort is really worthwhile, check it and contribute to it as you can.
Meeting who began all this "I want my data back" movement was ipercool as well: Libby Miller and Dan Brickley (creator of the first version of FOAF format) are our real FOAF queen and king. You can check my pictures of the workshop or find more of them tagged as #foaf-galway on del.icio.us.
Moreover, now that I have some real <foaf:knows> relations I promise I'll update very soon my FOAF file.
I also got 2 t-shirts so the goal I chose for the workshop was partially accomplished
Last thing I want to mention is: "never go to a restaurant in Galway!". I spent 35 + 42 +65 euros for the dinner. Every time (but the second dinner in the castle) it was kind of self-organized. Of course the goal of a workshop is to stay with other people and discuss, share ideas so going back to the hostel or eat something alone in some very cheap place was not an option but next time I'll be more reactive and suggest to everyone to go to cheaper places. The problem was that I was paying the workshop with my money and so almost 150 euros for 3 dinners were really too much for me! However I should mention that lunches were kindly offered by the DERI institute and that the hostel I found (sleepzone) was cheap enough (15 euros per night) and with free internet connection (8 computer with RedHat!) and free wireless connection to Internet as well.
All considered, it was a great workshop and I had fantastic time.
August 03, 2004
| FOAF |
foaf
|
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
Good news: my paper "Trust-aware Collaborative Filtering for Recommender Systems" got accepted for Coopis2004.
Bad news: the conference is hyper-expensive.
So I'm looking for hyper-cheap (possibly free) hospitality in Larnaca, Cyprus, from 25 Oct to 29 Oct 2004. I checked on couchsurfing (a site where people offers ospitality in their houses and a super-cool YASN [yes, you can express your friends list]) but I found none in Cyprus.
If we take for true the six degree of separation theorem, I should be connected to everyone in Cyprus by only six degrees of separation. So I guess there should be at least some cypriots in my friends of friends set, now i only need to find one of the connecting friends. So if you know someone in Cyprus, please become my friend and close the circuit (and don't forget to write down the path from me to the cypriot host in the comments below). Thanks.
June 22, 2004
| FOAF |
foaf
|
| PhD |
phd
|
| Social Software |
social_software
|
1st Workshop on Friend of a Friend, Social Networking and the Semantic Web (FOAF'2004)
*1-2 September 2004, Galway, Ireland*,
sponsored by SWAD-Europe and DERI
http://www.w3.org/2001/sw/Europe/events/foaf-galway/
Many of the interesting conferences about these topics happen in USA. So, if you are in Europe, you cannot miss this one!
In the committee there are many people that I learn to know by email or by reading their blogs but I have never met. I hope to meet them physically in Galway.
(found via rdfweb mailing list)
This call for papers also appears in the Call for papers topicexchange channel and in Trust-related-conferences wiki page
Introduction
------------
The FOAF (Friend of a Friend
project explores a unique combination of themes from social
networking, search engines, knowledge representation and software
development. FOAF was designed as a practical experiment that
would highlight the technical, social and business challenges
raised by the next generation of "Semantic" Web technology. Over
the past few years, the FOAF developer community has been working
on standards-based techniques for publishing and harvesting
machine-readable descriptions of people, the links between them,
and the things they create and do. The working assumption of the
project is that such techniques will underpin the deployment of
the next generation of Web technology, W3C's "Semantic Web".
The FOAF project was created in the expectation that
these machine-readable descriptions will grow, as the Semantic Web
platform matures, to cover companies, organisations, documents,
groups, products, file sharing and many other aspects of life,
both online and off. The time has come to evaluate these
assumptions in the context of the opportunities and challenges
presented by the rise of FOAF and the
Semantic Web.
Social networking is a recent topic gaining much interest and
publicity. Social networking sites are community sites where users
can maintain an online network of friends or associates for social
or business purposes: whether looking for a job, reconnecting with
old friends, moving to a new area, or dating. Most of these sites
are based on a centralised architecture: all users' descriptions
are stored in one big database. There is, however, growing user
and business interest in portability between such sites, and for
sophisticated "single sign-on" mechanisms that reduce the need for
data re-entry, while allowing users to manifest different aspects
of themselves in different contexts. FOAF-based import/export
allows such sites to address user demand for control of "their"
data; however, many deployment, privacy, authentication and
engineering issues have not yet been fully explored. To what
extent do mechanisms such as FOAF change the environment they
attempt to describe? How can the visibility of personal data be
restricted to certain audiences? How can businesses make money
when their customers can migrate to new services with increased ease?
This workshop on FOAF, social networking and the Semantic Web
provides a first chance to discuss the unusual combination of
perspectives - academic and scientific, engineering, social, legal
and business - drawn together by these trends. The workshop aims
to bring together for the first time researchers interested in the
effects, analysis and application of social networks on the
(Semantic) Web as well as practitioners building applications and
infrastructure. The workshop will also try to give a snapshot of
current developments, as well as setting a roadmap for the future
of both FOAF and social networking - especially in the context
of the Semantic Web.
Topics of interest for full papers include, but are not limited to
the following:
* Social network metadata standards
* Trust issues in social networks
* Profiles of FOAF, subsets, mapping to other vocabularies and formats
* Federated digital identity, single sign-on (decentralized identity
management)
* Business models for the Semantic Web (life after banner
advertisements)
* Integration with desktop and mobile applications (chat, IM, P2P,
Bluetooth, address books, RSS/Atom)
* Privacy, etiquette and best practice issues for aggregators
* Infrastructure for social networking
* Applications of online social networking
* Knowledge management with social networks
* Mathematical analysis of social networks
* Exchange of social network information
* Applications of online social networks
* Shared annotations
* Use of digital signatures and encryption with RDF/XML
* RDF-based search engines, data harvesting and syndication
* GUIs (browsers, editors) for FOAF and Semantic Web data
* Formalisms that address practical problems of heterogenous
changing data
* Pragmatics of sharing data schemas across subtly different datasets
Submission and Important Dates
------------------------------
The workshop will be organized in part around talks presenting
selected research results in the relevant fields. Another
important part of the workshop will be open discussions, where
participants define the agenda themselves, focusing on the
interests of the participants with respect to social networking,
FOAF, and the Semantic Web. Depending on the nature of the
submissions, some time may be allocated to discussion of
the future development and coverage of the FOAF specification.
We invite the submission of position statements and demonstration
descriptions as well as full papers. Position papers and
demonstration submissions should not exceed 1000 words, full
papers should not contain more than 6000 words. Documents should
be be submitted as tarred/zipped archives containing exactly one
index.html file and all accompanying files to
team-foafws-org at w3.org (or alternate address(danbri+foafws at w3.org>).
Papers to be published and/or presented will be selected by in
peer review process.
* Full paper submissions due: *18th July 2004*
* Position papers and demonstration proposals due: *22nd July 2004*
* Notification for acceptance: *5th August 2004*
* Web-ready versions due: *16th August 2004*
* Workshop date: *1st-2nd September 2004*
Chairs
------
* Dan Brickley
* Stefan Decker
* Libby Miller
* R.V.Guha
Programme Committee
-------------------
* Lada Adamic
* Tom Baker
* Orkut Buyukkokten
* Marc Canter
* Edd Dumbill
* Dieter Fensel
* Morten Frederiksen
* Nick Gibbins
* Jen Golbeck
* R.V.Guha
* Jan Hauser
* Jim Hendler
* Mashide Kanzaki
* Paul Martino
* Brian McBride
* Wolfgang Nejdl
* Chris Schmidt
* Guus Schreiber
* Nova Spivak
* Barney Pell
* Jack Park
* Danny Weitzner
Location
--------
Galway
13th century by the Anglo-Norman de Burgos as a medieval
settlement on the eastern bank of the River Corrib. It became a
walled and fortified city state ruled by fourteen powerful
merchant families, later known as the "Tribes of Galway". Today
the city is a vibrant, bustling centre of the arts and commerce,
though it still retains a relaxed and intimate atmosphere. Galway
is also one of the most popular tourist destinations in the
country. The city, with its medieval streets, waterways, extensive
range of shopping facilities, wealth of music sessions and other
cultural events, is a place to be treasured. The seaside town of
Salthill, a Galway suburb, is a renowned summer resort. Its fine
beaches open directly onto spectacular Galway Bay. Galway's
numerous annual festivals and celebrations - among them the
'C?irt' International Festival of Literature, the Galway Arts
Festival, the Galway Races and the Oyster Festival - are famous
throughout Ireland and beyond. Galwegians can justly claim a
quality of life that is surpassed nowhere in the world.
Being a university city, Galway is a lively energetic place
throughout the year. The National University of Ireland, Galway
enjoys an intimate relationship with the city and during the
academic year, 15% of the population of the city are students. A
compact, thriving city, Galway caters to youth like few other
places can. The University's graduates have played a pivotal role
in all areas of the development of Galway, including the arts,
industry and commerce.
The Digital Enterprise Research Institute
centre located at NUI Galway and is focused on developing
Semantic Web technology.
See the local organisers
page for further details on accommodation and travel.
Sponsoring Possibilities
------------------------
Are you a company or organisation willing to sponsor this event?
Sponsoring companies will be given the opportunity to present
their software in The demo session and display their logo
prominently on the workshop homepage. Please contact John Breslin
(john.breslin at deri.ie) for further information.
May 24, 2004
| FOAF |
foaf
|
| PhD |
phd
|
| Semantic web |
semantic_web
|
| Trust and Reputation |
trust_and_reputation
|
I'm writing a paper for Coopis2004 and have not too much time to blog. By the way, I'm in committee of 2 very interesting workshops:
- Trust, Security, and Reputation on the Semantic Web (held at the 3rd International Semantic Web Conference (ISWC) from 7-11 November, 2004 in Hiroshima, Japan.)
Deadline for Submissions: July 16, 2004
- Trust, Recommendations, Evidence and other Collaboration Know-how (TRECK) Track (track of the 20th ACM Symposium on Applied Computing, Santa Fe, New Mexico, March 13 -17, 2005)
Deadline for Submissions: Sept. 3, 2004
You are of course invited to submit challenging and innovative ideas!
I guess I should also update our wiki list of trust related conferences. In the meantime I ping http://topicexchange.com/t/calls_for_papers/
April 06, 2004
| Free software |
free_software
|
| PhD |
phd
|
| Programming |
programming
|
| Trust and Reputation |
trust_and_reputation
|
For my studies on trust metrics, I need to code trust metrics. I was looking for a Java package for modeling, analysis, and visualization of graphs (possibly weighted and directed). I tried many of them (see below) but I found a wonderful one!
Java Universal Network/Graph Framework hosted on SourceForge so open source under a BSD licence (javadoc).
JUNG — the Java Universal Network/Graph Framework--is a software library that provides a common and extendible language for the modeling, analysis, and visualization of data that can be represented as a graph or network. It is written in Java, which allows JUNG-based applications to make use of the extensive built-in capabilities of the Java API, as well as those of other existing third-party Java libraries.
The current distribution of JUNG includes implementations of a number of algorithms from graph theory, data mining, and social network analysis, such as routines for clustering, decomposition, optimization, random graph generation, statistical analysis, and calculation of network distances (Dijkstra Shortest Path), flows, and importance measures (centrality, PageRank, HITS, Random Walk, etc.).
JUNG also provides a visualization framework that makes it easy to construct tools for the interactive exploration of network data. Users can use one of the layout algorithms provided, or use the framework to create their own custom layouts. In addition, filtering mechanisms are provided which allow users to focus their attention, or their algorithms, on specific portions of the graph.
If you don't trust me, you can try the Ranking Demo or the other demos.
It is of course an evolving project, I already wrote some code to draw arrows and to label edges with weights and I'm trying to integrate it. I plan to code some of these trust metrics. JUNG is maintained by some great PhD students.
Other packages I tried and didn't fit my needs: JGraphT (visualizable with Jgraph), JGraph, jdigraph, The Data Structures Library in Java.
Other packages I quickly analyzed without downloading them and trying them and not meeting my needs either (especially because focusing only on graph visualization): Graph Foundation Classes for Java (It is by IBM but it is retired and no longer available), OpenJGraph - Java Graph and Graph Drawing Project, Touchgraph (wonderful for visual interaction with drawn graphs), Grappa (A Java GRAPh PAckage), JGraphEd, Graph Editing Framework, GVF - The Graph Visualization Framework, Graph Mapper, VGJ, Visualizing Graphs with Java
Many of these packages (and some more) can be found searching graph on java-channel.org
February 27, 2004
I realised today I didn't write yet an entry about my PhD Research Proposal "Trust-aware Decentralized Recommender Systems" (TaDRS).
So here it is the PDF file. If you have any comment or criticism, I'll be happy to hear from you.
The PhD research proposal is a little bit outdated (29th May 2003) but I didn't have a blog at that time. Enjoy and let me know what you think.
UPDATE:
Abstract
This PhD thesis addresses the following problem: exploiting of trust information in order to enhance the accuracy and the user acceptance of current Recommender Systems (RS). RSs suggest to users items they will probably like. Up to now, current RSs mainly generate recommendations based on users' opinions on items. Nowadays, with the growth of online communities, e-marketplaces, weblogs and peer-to-peer networks, a new kind of information is available: rating expressed by an user on another user (trust). We analyze current RS weaknesses and show how use of trust can overcome them. We proposed a solution about exploiting of trust into RSs and underline what experiments we will run in order to test our solution.
February 02, 2004
It is already 2 weeks since I came back to Italy but I haven't had time to realize it.
I have spent the past 3 months at the Computer Science department of University of Maryland and it was a very useful and interesting period.
It was also my first time in USA. The Univ of Maryland is a wonderful place for doing research.
It is difficult to compare it with anything in Italy. I believe the Univ of Trento where I'm doing the PhD in Information and Communication Technologies is one of the best in Italy [as statistics (in Italian) confirm]. Anyway it is difficult to have a good national research if the miserabile Italian government invests only 1% of GDP in Research.
By the way, what I especially liked of UMD is:
1. Every workgroup has a weekly meeting in which one member of the group presents a paper (not necessarily one of her papers).
2. CS department offers a weekly coffee break: the idea is you go there, have a coffee and a cookie and chat with your collegues. This is very good for cross-fertilization and collaboration.
3. Usually 30 minutes before a talk there is coffee break where you can talk with the speaker and other people.
4. Sometimes after a talk there is a meeting with the speaker for everyone is interested.
Yeah, I know, it seems being a researcher is just having coffee with people...
January 29, 2004
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
Since Seb ha cited my paper as epinions empirical analysis paper, I'd like to mention other 2 papers that analyze epinions web of trust:
the already commented Trust Management for the Semantic Web and the new Propagation of Trust and Distrust.
As a side point, note that we collected datasets of different dimensions. I collected only 49.290 Epinions users because I was following only "this user trusts X" links. Richardons et al. collected 75.000 users (but used only 5.000 of them); I think they followed also "this user is trusted by" links. Guha et al. had access to the real dataset of Epinions which consists of 130.000 users. Note also that Guha et al. had access also to the web of distrust (a sort of black list) while this information is not available on Epinions.com and hence not downloadable.
This post also appears on channel social software
December 16, 2003
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Social Software |
social_software
|
| Trust and Reputation |
trust_and_reputation
|
I submitted my paper Using Trust in Recommender Systems: an Experimental Analysis to the Second International Conference on Trust Management 2004.
You can read the PDF file or the HTML version (by latex2html).
Abstract:
Recommender systems (RS) have been used for suggesting items (movies, books, songs, etc.) that users might like. RSs compute a user similarity between users and use this as a weight for the users' ratings. However they have many weaknesses, such as sparseness, cold start and vulnerability to attacks. We assert that these weaknesses can be alleviated using a Trust-aware system that takes into account the ``web of trust'' provided by every user.
Specifically, we analyze data from the popular Internet web site epinions.com. The dataset consists of 49290 users who expressed reviews (with rating) on items and explicitly specified their web of trust, i.e. users whose reviews they have consistently found to be valuable.
We show that users have usually few items rated in commons. For this reason, the classic RS technique is often ineffective and is not able to compute a user similarity weight for many of the users. Instead exploiting the webs of trust, it is possible to propagate trust and infer an additional weight for other users. We show how this quantity can be computed against a larger number of users.
October 30, 2003
| Maryland |
maryland
|
| Peer to peer |
peer_to_peer
|
| PhD |
phd
|
| Recommender Systems |
recommender_systems
|
| Trust and Reputation |
trust_and_reputation
|
As part of my PhD program, I'll spend the next 3 months at the University of Maryland. I'll stay here until January 17, 2003.
I also opened up a photo gallery in which I'll post photos taken here.
