An algorithm for drawing general undirected graphs
Information Processing Letters
Comments-oriented blog summarization by sentence extraction
Proceedings of the sixteenth ACM conference on Conference on information and knowledge management
CIT '09 Proceedings of the 2009 Ninth IEEE International Conference on Computer and Information Technology - Volume 02
How useful are your comments?: analyzing and predicting youtube comments and comment ratings
Proceedings of the 19th international conference on World wide web
| Hi-index | 0.00 |
In online communities, such as blogs or Inter forum sites, readers usually express their opinions by adding replying comments and understand others' views by reading them. Especially, in Internet forum site, many users discuss and dispute with others by a series of replying comments. This implies that a series of comments can be a new source of information, particularly revealing the dispute relations of users. Unfortunately, the current viewing systems of replying comments is very primitive and it is hard to figure out the dispute sections and relations. In this paper, we propose a new system for automatically detecting the dispute sections and relations from a large set of replying comments. The basic idea is exploiting the order of posting time of comments with the commenter information, for the comments in a dispute section tend to appear in turns. The proposed system does not only detect the dispute sections but also visualize it with the dispute relations among commenters. The system is highly effective to help the users to grasp the controversial structure of comments. According to the experimental results, the accuracy of the proposed detection method is 83% on average.