作者: Feng Xiao , Tomoya Noro , Takehiro Tokuda
DOI: 10.1007/978-3-642-31753-8_2
关键词:
摘要: Hashtags, which started to be widely used since 2007, are always utilized mark keywords in tweets categorize messages and form conversation for topics Twitter. However, it is hard users use hashtags sharing their opinions/interests/comments interesting topics. In this paper, we present a new approach recommending news-topic oriented help Twitter easily join the about news We first detect topic-specific informative words co-occurring with given target word, call characteristic co-occurrence words, from articles vector representing topic. Then by creating hashtag based on same hashtag, calculate similarity between these two vectors recommend of high scores Experimental results show that our could highly relevant topics, helping share others