Social summarization of text feedback for online auctions and interactive presentation of the summary

Buyers in online auctions write feedback comments to the sellers from whom they have bought the items. Other bidders read them to determine which item to bid for. In this research, we aim at helping bidders by summarizing the feedback comments. First, we examine feedback comments in online auctions. From the results of the examination, we propose a method called social summarization method. It uses social relationships in online auctions for summarizing feedback comments. This method extracts feedback comments which the buyers seemed to have written from their heart. We implement a system based on our method and evaluate its effectiveness. The results are that our method deleted 80.8% of courteous comments (comments with almost no information). We also found that there are two types of comments in the summaries: comments that are generally infrequent and seem to have been written with real feeling and comments that are generally frequent and seem to have been written with real feeling. Finally, we propose an interactive presentation method of the summaries which identifies the types of the comments. The user experiment indicates that this presentation helps users judge which seller to bid for.