The First Workshop on Information Credibility on the Web (WICOW)
in conjunction with
The 21st Annual Conference of the Japanese Society for Artificial Intelligence (JSAI 2007)

Phoenix Seagaia Resort (Miyazaki, Japan)
June 19, 2007

WICOW-3 is planned at WWW 2009

WICOW-2 was held at CIKM 2008

Selected papers from the workshop have been published in a special issue of Internet Research

Final Program

Accepted Papers

Last Update: 2009-01-27

Description

As computers and computer networks become more sophisticated, a huge amount of text-based information, such as that found in web documents, emails, and business related documents has been accumulated and circulated. Such information gives people a framework for organizing their daily life. Moreover, this information is starting to have a strong influence on governmental policy, and how businesses are managed. A well-functioning society needs technology that can be used to manage this wealth of text-based information. This technology would be able to handle a wide range of tasks: extracting credible information related to a given topic (particularly when the query has returned answers from large documents); organizing this information; clarifying the background, the facts, and the various opinions and the distribution of them, and so on. The aim of this workshop is to provide a forum for discussion on issues related to information credibility criteria.

Areas of Interest

The workshop will focus on how to evaluate the credibility of information. In particular, contributions will be solicited which address, but are not limited to, the following areas of interest:

  • Information content analysis for credibility evaluation (topic extraction, opinion analysis, etc.).
  • Identification and characterization of the sender to enable the user to evaluate their credibility.
  • Information credibility evaluation based on superficial characteristics of information.
  • Information credibility evaluation based on reputation.
  • Information credibility evaluation for user-generated content (blogs, SNSs, etc.).
  • The relationship between information credibility evaluation and the concepts of trust and credibility.
  • Sociological aspects of information credibility.
  • Psychological aspects of information credibility.
  • Utilization of social networks for information credibility evaluation.
  • Issues concerning credibility of grassroots/citizen journalism.
  • Establishing information dissemination processes that promote the dissemination of credible information.

Invited Speaker

Yunbo Cao (Microsoft Research Asia)

Yunbo Cao is an associate researcher at Microsoft Research Asia. His current research interests include text mining, question answering, and machine learning. He is very active in the research communities. So far, he has about 20 quality papers published in referred international conferences and journals and has over 10 filed US/international patents or pending applications. He has served on the program committees for several international conferences, including SIGIR, NAACL-HLT, and AIRS. He is also a reviewer for international journals such as IEEE Transaction on Knowledge and Data Engineering, Pattern Recognition Letters, and Journal of Computer Science and Technology. Prior to joining Microsoft, Yunbo Cao obtained his B.S. on Probability & Statistics and M.S. on Computer Science from Peking University. Now he is also a PHD candidate on Computer Science at Shanghai Jiaotong University.

Title: Assessing Quality of Product Reviews

In the past few years, there has been an increasing interest in mining opinions from product reviews [3][4][5]. However, due to the lack of editorial and quality control, reviews on products vary greatly in quality. Thus, it is crucial to have a mechanism capable of assessing the quality of reviews and detecting low-quality and noisy reviews.
Some shopping sites already provide a function of assessing the quality of reviews. For example, Amazon2 allows users to vote for the helpfulness of each review and then ranks the reviews based on accumulated votes. However, according to our survey, users’ votes at Amazon have three kinds of biases as follow:

1) Imbalance vote bias -- users tend to value others’ opinions positively rather than negatively. As the result, most reviews are considered as high-quality ones;
2) Winner circle bias -- the more votes a review gains, the more default authority it would appear to readers, which in turn will influence the objectivity of the readers’ votes. As the result, a few reviews receive most of users’ votes;
3) Early bird bias -- the earlier a review is posted, the more votes it will get. Therefore, some high-quality reviews may get fewer users’ vote because of later publication.

Existing studies [2][6] used these users’ votes for training ranking models to assess the quality of reviews, which therefore are subject to these biases. In our research, we identify the aforementioned biases and define a standard specification to measure the quality of product reviews. We then manually annotate a set of ground-truth with real world product review data conforming to the specification.

[Download the extended abstract]

Note: the topic of the talk has been changed from expert search to the one shown above.

Registration

Registration will be done on-site. Registration fee is 5,000 JPY.

Accomodation

There are several options for accomodation. One option is to stay at a hotel in the area of Phoenix Segaia Resort. There are three hotels in the area as listed below. The other option is to stay in the city center, from which it takes about 20-30 minutes by taxi to the conference site. JTB is arranging travels for the workshop participants, and you can contact them to make a hotel reservation. Please refer to JSAI2007 conference when you make a booking. More information is available in Japanese at the following site:
https://act.jtbgmt.com/gmt/ssl/ai-gakkai2007j.asp

Hotels in the Phoenix Seagaia Resort Area:

No.

Hotel

(Check In/ Check Out)

 

Fare (Per Room)

Description

Single

(1 Person)

Twin

(2 Persons)

(1) Sheraton Grande Ocean Resort
14:30/11:00
*14,700 JPY *17,850 JPY

21,000 JPY
25,200 JPY

Tel: 0985-21-1111
32 min. from the airport by bus. Near the conference site.

(2) Sun Hotel Phoenix
14:00/11:00
*8,400 JPY *10,500 JPY 13,650 JPY
18,900 JPY
Tel: 0985-39-3131
32 min. from the airport by bus. Near the conference site.
(3) Cottage Himuka
14:00/11:00

Single
*10,500 JPY
*14,700 JPY

Twin
10,500 JPY 14,700 JPY

Triple
12,600 JPY 18,900 JPY

Tel:0985-21-1355
32 min. from the airport by bus. Near the conference site.

*Single use of double or twin room.

Hotel Reservation:

JTB Global Marketing and Travel, JSAI2007 Desk
Office Hours: From 9:30 to 17:30 on weekdays (closed on weekend and on holidays)
Address: 2-3-11 Higashi-Shinagawa, Shinagawa, Tokyo 140-8604
Phone: +81-3-5796-5445
Fax: +81-3-5495-0685
E-mail: ai-gakkai2007@jtb.jp

Submission Instructions

Manuscripts should be prepared using the Springer's LNCS style with the maximum of 8 pages in PDF format. Please send your manuscript to the workshop chairs by e-mail.

Working Notes and Post-proceedings

Working notes of the workshop will be published with ISBN by JSAI. Negotiations are under way between JSAI and Springer to have selected papers from the workshop to be published as post-proceedings in the Springer LNAI series.

Important Dates

  • March 30, 2007 April 8, 2007
    Deadline for paper submission
    s
  • April 13, 2007 April 29, 2007
    Notification
  • April 27 , 2007 May 21, 2007
    Deadline for camera-ready versions

Workshop Chairs

Sadao Kurohashi
Department of Intelligence Science and Technology
Kyoto University
Sakyo, Kyoto, 606-8501, Japan
kuro (at) i.kyoto-u.ac.jp
http://nlp.kuee.kyoto-u.ac.jp/~kuro/

Kentaro Inui
Graduate School of Information Science
Nara Institute of Science and Technology
Keihanna, Nara, 630-0192, Japan
inui (at) is.aist-nara.ac.jp
http://cl.aist-nara.ac.jp/~inui/

Yoshikiyo Kato
Knowledge Creating Communication Research Center
National Institute of Information and Communications Technology
3-5 Hikaridai, Seika, Soraku, Kyoto 619-0289, Japan
ykato (at) nict.go.jp
http://kc.nict.go.jp/ykato/

Program Committee

  • Kentaro Inui (Nara Institute of Science and Technology, Japan)
  • Yoshikiyo Kato (National Institute of Information and Communications Technology, Japan)
  • Sadao Kurohashi (Kyoto University, Japan)
  • Hang Li (Microsoft Research Asia)
  • Yutaka Matsuo (National Institute of Advanced Industrial Science and Technology, Japan)
  • Hisashi Miyamori (National Institute of Information and Communications Technology, Japan)
  • Manabu Okumura (Tokyo Institute of Technology, Japan)
  • Noboru Sonehara (National Institute of Informatics, Japan)
  • Hideaki Takeda (National Institute of Informatics, Japan)
  • Katsumi Tanaka (Kyoto University, Japan)