WICOW 2009 is going to be
organized in conjunction with
the 18th World Wide Web Conference in Madrid, Spain
WICOW 2008 proceedings are available in ACM Digital library.
As computers and computer networks become more sophisticated, a huge amount of information, such as that found in Web documents, has been accumulated and circulated. Such information gives people a framework for organizing their daily lives. A well-functioning society needs technology that can be used to manage this wealth of information and, in particular, investigate its credibility. This technology would be able to handle a wide range of tasks: extracting credible information related to a given topic, organizing this information, detecting its provenance, clarifying background, facts, and various related opinions and the distribution of them, and so on. Especially, as the Web is becoming a major source of information nowadays, it is necessary to provide efficient and reliable methods for evaluation of Web content's trustworthiness. The aim of this workshop is to provide a forum for discussion on issues related to information credibility criteria and the process of its evaluation.
We invite submissions on any aspects of Information Credibility on the Web. Topics include, but are not limited to:
8.30 - 10.30 Session 1: Analyzing Social Networks and Discussion Forums
1st keynote: Graph Mining and Influence Propagation
10:30 - 11:00 Coffee Break
11:00 - 12:40 Session 2: Web Content Analysis
2nd keynote: Information Credibility Analysis of Web Content (presentation(30MB))
12:40 - 14:00 Lunch
14:00 - 15:30 Session 3: Content Aggregation on the Web
The presentations of full and short papers are scheduled to take 25min and 20min, respectively, including questions.
TITLE: Graph Mining and Influence Propagation
SPEAKER: Christos Faloutsos (CMU)
How do graphs look like? How do they evolve over time? How can we generate realistic-looking graphs? We review some static and temporal laws, and we describe the "Kronecker" graph generator, which naturally matches all of the known properties of real graphs. We also describe some case studies. The first is on influence and virus propagation on real graphs, where we show that the so-called "epidemic threshold" of a graph depends only on the first eigenvalue of the adjacency matrix. The second shows how to spot patterns in e-bay interaction graphs, indicative of the "non-delivery" type of fraud. The last is analysis on blog cascades and some surprising patterns there.
Christos Faloutsos is a Professor at Carnegie Mellon University. He has received the Presidential Young Investigator Award by the National Science Foundation (1989), the Research Contributions Award in ICDM 2006, twelve "best paper" awards, and several teaching awards. He has served as a member of the executive committee of SIGKDD; he has published over 160 refereed articles, 11 book chapters and one monograph. He holds five patents and he has given over 20 tutorials and over 10 invited distinguished lectures. His research interests include data mining for streams and networks, fractals, indexing for multimedia and bio-informatics data, and database performance.
TITLE: Information Credibility Analysis of Web Content (presentation(30MB))
SPEAKER: Yutaka Kidawara (NICT)
General users write daily news about themselves and post information they consider interesting as digital documents for blogs and SNS. Such digital content includes both valuable information as well as worthless, false, and demagogic information. Ordinary web search engines can display web pages in a particular order. The ranking method evaluates the score of web content and generates a ranked list. The top-ranked web content on search engines is often relevant to the user's query, though, in some cases, the content may not be credible or valuable. Nevertheless, readers often trust the authenticity of the displayed information. Even if users believe that the content is useful, the search engine cannot evaluate the retrieved digital content, and users have to retrieve a variety of content using different keywords. The need for an information analysis technology that helps find credible and valuable information from large amounts of Web content is progressively growing.
In Japan, the NICT (National Institute of Information and Communications Technology) initiated the "Information Credibility Criteria Project" in 2006, and the MIC (Ministry of Internal Affairs and Communications), too, initiated the "Research and Development of Information Credibility Verification Technology for Telecommunication Service" in 2007. The NICT's project addresses the issue of information credibility by analyzing credibility based on the following criteria: (1) content, (2) sender, (3) appearance, and (4) authenticity of content. We believe that the understanding of texts by a machine is important and that an NLP (Natural Language Processing) approach is very effective in evaluating the credibility criteria. The MIC's project aims to develop methods to analyze not only text information but also multimedia content using NLP, information retrieval and data mining approaches. By using different methods for analyzing the information credibility criteria, credible information can be acquired, which eventually becomes valuable knowledge. This talk will throw light on the activities of both projects in Japan.
Dr. Yutaka Kidawra is a group leader of the Knowledge Clustered Group of the NICT in Japan. He received his B.E., M.E., and Ph.D. degrees from Kobe University in 1988, 1990, and 2000, respectively. He was a deputy director for the Information and Communications Technology division of the Council for Science and Technology Policy, Cabinet Office Government of Japan in 2006, a senior researcher at the NICT/CRL from 2001 to 2005, and a researcher at Kobe Steel Ltd. from 1990 to 2000. His current research interests include information credible analysis, knowledge processing, database systems, and ambient intelligence technologies.
"On the Credibility of Wikipedia: an Accessibility Perspective" (presentation)
Rui Lopes (University of Lisbon, Portugal), Luis Carriço (University of Lisbon, Portugal)
"Reasonable Tag-Based Collaborative Filtering" (presentation(5.3MB))
Reyn Nakamoto (Kizasi Company, Japan), Shinsuke Nakajima (Kyoto Sangyo University, Japan), Jun Miyazaki (NAIST, Japan), Shunsuke Uemura (Nara Sangyo University, Japan), Hirokazu Kato (NAIST, Japan), Youichi Inagaki (Kizasi Company, Japan)
"Using a Sentiment Map for Visualizing Credibility of News Sites on
the Web" (presentation(2.3MB))
Yukiko Kawai (Kyoto Sangyo University, Japan), Yusuke Fujita (Kyoto Sangyo University, Japan), Tadahiko Kumamoto (Chiba Institute of Technology, Japan), Jianwei Zhang (Kyoto Sangyo University, Japan), Katsumi Tanaka (Kyoto University, Japan)
"Detecting Reviewer Bias through Web-Based Association Mining" (Best paper award)
Richard Chow (Palo Alto Research Center, USA), Jessica Staddon (Palo Alto Research Center, USA)
"PodCred: A Framework for Assessing Podcast Credibility" (Best paper award) (presentation(1.9MB))
Manos Tsagkias (University of Amsterdam, The Netherlands), Martha Larson (University of Amsterdam, The Netherlands), Wouter Weerkamp (University of Amsterdam, The Netherlands), Maarten de Rijke (University of Amsterdam, The Netherlands)
"A Metacognitive Approach to Credibility Determination" (presentation)
Marie Iding (University of Hawaii, USA), Brent Auernheimer (California State University, USA), Martha E. Crosby (University of Hawaii, USA)
"Automatic Scoring of Online Discussion Posts"
Nayer Wanas (Cairo Microsoft Innovation Center, Egypt), Motaz El-saban (Cairo Microsoft Innovation Center, Egypt), Heba Ashour (Cairo Microsoft Innovation Center, Egypt), Waleed Ammar (Cairo Microsoft Innovation Center, Egypt)
"Extracting the Author of Web Pages" (presentation(1.2MB))
Yoshikiyo Kato (NICT, Japan), Daisuke Kawahara (NICT, Japan), Kentaro Inui (NAIST, Japan), Sadao Kurohashi (NICT and Kyoto University, Japan), Tomohide Shibata (Kyoto University, Japan)
"ALPACA: A Lightweight Platform for Analyzing Claim
Jeff King (Georgia Institute of Technology, USA), Jennifer Stoll (Georgia Institute of Technology, USA), Michael Hunter (Georgia Institute of Technology, USA), Mustaque Ahamad (Georgia Institute of Technology, USA)
"A Characteristic Based Information Evaluation Model"
Llewellyn Tang (Loughborough University, UK), Yuyang Zhao (University of Bath, UK), Simon Austin (Loughborough University, UK), Mansur Darlington (University of Bath, UK), Steve Culley (University of Bath, UK)
"Can Social Annotation Support Users in Evaluating the
Trustworthiness of Video Clips?"
Satoshi Nakamura (Kyoto University, Japan), Makoto Shimizu (Kyoto University, Japan), Katsumi Tanaka (Kyoto University, Japan)
"Web-based Evidence Excavation for Exploring Authentic Local
Ryong Lee (University of Hyogo, Japan), Daisuke Kitayama (University of Hyogo, Japan), Kazutoshi Sumiya (University of Hyogo, Japan)
"Improving information quality in email exchanges by identifying
entities and related objects" (presentation(1.7MB))
Marek Kowalkiewicz (SAP Research, Australia), Konrad Juenemann (SAP Research, Australia)
"Professional Credibility: Authority on the Web" (presentation)
Jack G. Conrad (Thomson Reuters, USA), Frank Schilder (Thomson Reuters, USA), Jochen Leidner (Thomson Reuters, UK)
"A "Quick and Dirty" Website Data Quality Indicator" (presentation)
Irit Askira Gelman (University of Arizona, USA), Anthony Barletta (University of Arizona, USA)
Submissions should be sent in English in PDF format via the submission website. Papers should adhere to ACM formatting guidelines. They must be original and have not been submitted for publication elsewhere. We encourage also submission of position papers outlining interesting research directions.
The accepted papers are going to appear in CIKM Workshops Proceedings published by ACM either as full (up to 8 pages) or short papers (up to 4 pages) depending on the review results. At least one author of each accepted submission should register by the end of the early registration period for the paper to be included in the proceedings.
Best papers from the workshop can be invited for a special issue in a relevant international journal or a book and the workshop report is planned to be published after the workshop.
National Institute of Information and Communications Technology
Kyoto University Global COE Program: Informatics Education and Research for Knowledge-Circulating Society
email: adam [at] dl [dot] kuis [dot] kyoto-u [dot] ac [dot] jp