Classifying Behaviors of Information Cascades on Multi Social Media

2015 Fiscal Year Final Research Report

• Project/Area Number: 25280111
• Research Category: Grant-in-Aid for Scientific Research (B)
• Allocation Type: Partial Multi-year Fund
• Section: 一般
• Research Field: Web informatics, Service informatics
• Research Institution: The University of Tokyo
• Principal Investigator: TOYODA Masashi 東京大学, 生産技術研究所, 准教授 (60447349)
• Co-Investigator(Renkei-kenkyūsha): ITOH Masahiko 東京大学, 生産技術研究所, 特任准教授 (60466422)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: ソーシャルウェブ / 社会ネットワーク分析

Outline of Final Research Achievements

Information cascade through friendship networks is one of the most important phenomena on social media. We analyzed information cascades on heterogeneous topics, and investigated how their cascading behaviors affected by features, such as contents, paths of cascades, involved users, and languages. Based on the analysis, we proposed methods for classifying cascades by their social influence, and for predicting occurrence of cross-lingual cascades. Finally, we developed a system for visualizing cascading behaviors.

Free Research Field

情報学