Acquiring the Gist of Social Network Service Threads via Comparison with Wikipedia

Acquiring the Gist of Social Network Service Threads via Comparison with Wikipedia

Akiyo Nadamoto (Konan University, Japan), Eiji Aramaki (The University of Tokyo, Japan), Takeshi Abekawa (National Institute Informatics, Japan) and Yohei Murakami (National Institute of Information and Communications Technology, Japan)
DOI: 10.4018/jbdcn.2011040102
OnDemand PDF Download:
No Current Special Offers


Internet-based social network services (SNSs) have grown increasingly popular and are producing a great amount of content. Multiple users freely post their comments in SNS threads, and extracting the gist of these comments can be difficult due to their complicated dialog. In this paper, the authors propose a system that explores this concept of the gist of an SNS thread by comparing it with Wikipedia. The granularity of information in an SNS thread differs from that in Wikipedia articles, which implies that the information in a thread may be related to different articles on Wikipedia. The authors extract target articles on Wikipedia based on its link graph. When an SNS thread is compared with Wikipedia, the focus is on the table of contents (TOC) of the relevant Wikipedia articles. The system uses a proposed coverage degree to compare the comments in a thread with the information in the TOC. If the coverage degree is higher, the Wikipedia paragraph becomes the gist of the thread.
Article Preview


As Internet-based social network services (SNS's) have grown increasingly popular they are producing a great amount of content. An SNS consists of an Internet community, containing multiple threads, with each thread containing comments posted by multiple users. It is difficult to obtain a gist of a thread because these comments are complicated. There are two types of SNS users. The first type becomes a member of the community and discusses the theme of the thread. We call this user an “inside user.” The second type, an “outside user,” is a casual browser who simply views the SNS to acquire information from it.

Inside users can sometimes enter into heated discussion, which prompts them to concentrate on only one issue and lose track of the actual theme. When this happens, inside users may want to know how relevant their points are to the discussion. We therefore believe it would be beneficial to present these users with information to help them understand the gist of the discussion at a glance.

Outside users can theoretically obtain detailed information on the theme of a thread from the SNS, since community members who are inside users have good knowledge about the theme. Inside users, however, often do not explicitly provide basic information, because this is considered to be tacit knowledge, making it difficult for outside users to obtain. Moreover, a thread might contain many comments from outside users, making it difficult again to grasp the gist. It would be convenient for outside users to obtain the gist of a thread at a glance, while at the same time acquiring basic information about it.

In this paper, we propose a system that presents the gist of an SNS thread's information by comparing the comments in the thread with Wikipedia article content. Wikipedia articles are posted by different users on the basis that a “neutral point of view is the fundamental principle of Wikipedia” (Wikipedia, 2011). We therefore consider a Wikipedia article on a given theme to be based on a general viewpoint. In the present study, we extract articles from Wikipedia and compare each comment in a thread in the community content with the smallest structure in the article's table of contents (TOC). We consider the table of contents in the articles of Wikipedia to be the gist and the content of a paragraph on Wikipedia as basic information.

In this paper, we define a “target thread” as one from which the gist is to be extracted, and a “target article” as an article on Wikipedia that is to be compared with the target thread. The process of extracting a gist and basic information is as follows (Figure 1 and Figure 2):

Figure 1.

Illustration of comparison of an SNS thread with Wikipedia article

Figure 2.

Comparison between a target thread and a target article in our system

  • Extract noisy comments from a target thread.

  • Identify target articles on Wikipedia.

  • Compare the target thread and target articles on the basis of the table of contents based on our coverage degree.

  • Extract the gist of information about the target thread.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 18: 2 Issues (2022): Forthcoming, Available for Pre-Order
Volume 17: 2 Issues (2021)
Volume 16: 2 Issues (2020)
Volume 15: 2 Issues (2019)
Volume 14: 2 Issues (2018)
Volume 13: 2 Issues (2017)
Volume 12: 2 Issues (2016)
Volume 11: 2 Issues (2015)
Volume 10: 4 Issues (2014)
Volume 9: 4 Issues (2013)
Volume 8: 4 Issues (2012)
Volume 7: 4 Issues (2011)
Volume 6: 4 Issues (2010)
Volume 5: 4 Issues (2009)
Volume 4: 4 Issues (2008)
Volume 3: 4 Issues (2007)
Volume 2: 4 Issues (2006)
Volume 1: 4 Issues (2005)
View Complete Journal Contents Listing