TREC 2011 Microblog Track Experiments at Kobe University
Taiki Miyanishi, Naoto Okamura, Xiaoxi Liu, Kazuhiro Seki, Kuniaki Uehara · Text REtrieval Conference · 2011
This paper describes our approach to real-time ad hoc task processing in the TREC 2013 microblog track. The approach uses a concept-based query expansion method based on a temporal relevance model that uses the temporal variation of concepts (e.g. terms or phrases) on microblogs. Our model extends an effective existing word and concept-based relevance models by tracking the concept frequency over time in microblogging services. The experimentally ob- tained results demonstrate that our concept-based query expansion method im- prove search performance, especially when using tweet selection feedback.