Discussion Visualization Based on Analysis of Comments to Web News

Abstract

Opportunities for conducting discussions and expressing opinions on the Web have increased. It is desirable to fully understand the processes and main points of such discussions. In particular, it is important to understand both the main points of discussions and trends of opinions together rather than superficial results. However, such understanding is often difficult since the number of utterances increases as time passes and discussions become complicated. In this research, we aimed at developing methods for visualizing discussions in comments to Web news so that novices can understand both the main points and trends of opinions. This paper mainly overviews a prototype of a discussion visualization system.