作者: Makbule Gulcin Ozsoy , Kezban Dilek Onal , Ismail Sengor Altingovde
DOI: 10.1007/978-3-319-11746-1_6
关键词:
摘要: Being one of the most popular microblogging platforms, Twitter handles more than two billion queries per day. Given users’ desire for fresh and novel content but their reluctance to submit long descriptive queries, there is an inevitable need generating diversified search results cover different aspects a query topic. In this paper, we address diversification in tweet by adopting several methods from text summarization web domains. We provide exhaustive evaluation all using standard dataset specifically tailored purpose. Our findings reveal that implicit are promising current setup, whereas explicit be augmented with better representation sub-topics.