Search results

This aim of this paper is to elucidate rumor propagation on microblogs and to assess a system for collecting rumor information to prevent rumor-spreading.

We present a case study of how rumors spread on Twitter during a recent disaster situation, the Great East Japan earthquake of March 11, 2011, based on comparison to a normal situation. We specifically examine rumor disaffirmation because automatic rumor extraction is difficult. Extracting rumor-disaffirmation is easier than extracting the rumors themselves. We classify tweets in disaster situations, analyze tweets in disaster situations based on users' impressions and compare the spread of rumor tweets in a disaster situation to that in a normal situation.

The analysis results showed the following characteristics of rumors in a disaster situation. The information transmission is 74.9 per cent, representing the greatest number of tweets in our data set. Rumor tweets give users strong behavioral facilitation, make them feel negative and foment disorder. Rumors of a normal situation spread through many hierarchies but the rumors of disaster situations are two or three hierarchies, which means that the rumor spreading style differs in disaster situations and in normal situations.

The originality of this paper is to target rumors on Twitter and to analyze rumor characteristics by multiple aspects using not only rumor-tweets but also disaffirmation-tweets as an investigation object.

Community‐type content that are social network services and blogs are maintained by communities of people. Occasionally, community members do not understand the nature of the content from multiple perspectives, and so the volume of information is often inadequate. The authors thus consider it necessary to present users with missing information. The purpose of this paper is to search for the content “hole” where users of community‐type content missed information.

The proposed content hole is defined as different information that is obtained by comparing community‐type content with other content, such as other community‐type content, other conventional web content, and real‐world content. The paper suggests multiple types of content holes and proposes a system that compares community‐type content with Wikipedia articles and identifies the content hole. The paper first identifies structured keywords from the community‐type content, and extracts target articles from Wikipedia using the keywords. It then extracts other related articles from Wikipedia using the link graph. Finally, it compares community‐type content with the articles in Wikipedia and extracts and presents content holes.

Information retrieval looks for similar data. In contrast, a content‐hole search looks for information that is different. This paper defines the type of content hole on the basis of viewpoints. The proposed viewpoints are coverage, detail, semantics, and reputation.

The paper proposes a system for extracting coverage content holes. The system compares community‐type content with Wikipedia and extracts content holes in the community‐type content.