出版社：Japan Society for Fuzzy Theory and Intelligent Informatics
摘要：Online contents such as bulletin board services (BBSs) have recently gained a lot of attention as new tools for market analysis. In online games, where the contents must be accordingly updated after their releases in order to have users addicted to the games, it is important to grasp users' demands, and for this task BBSs and chat messages have been used. In this paper, we focus on the relations between comment replies, and propose a new method for discovering keywords by measuring influence rates in BBSs.
