Authors: Ayan Bandyopadhyay; Kripabandhu Ghosh; Prasenjit Majumder; Mandar Mitra
Addresses: IR Lab, CVPR Unit, ISI (Kolkata), 203 B.T. Road, Kolkata 700108, India ' IR Lab, CVPR Unit, ISI (Kolkata), 203 B.T. Road, Kolkata 700108, India ' DAIICT Gandhinagar, Near Indroda Circle, Pin-382007, India ' IR Lab, CVPR Unit, ISI (Kolkata), 203 B.T. Road, Kolkata 700108, India
Abstract: The extreme brevity of Microblog posts (such as 'tweets') exacerbates the well-known vocabulary mismatch problem when retrieving tweets in response to user queries. In this study, we explore various query expansion approaches as a way to address this problem. We use the Web as a source of query expansion terms. We also tried a variation of a standard pseudo-relevance feedback method. Results on the TREC 2011 Microblog test data (TWEETS11 corpus) are very promising - significant improvements are obtained over a baseline retrieval strategy that uses no query expansion. Since many of the TREC queries were oriented towards the news genre, we also tried using only news sites (BBC and NYTIMES) in the hope that these would be a cleaner, less noisy source for expansion terms. This turned out to be counter-productive.
Keywords: microblog search; tweet search; short text search; query expansion; query reformulation; query enrichment; microblog retrieval; microblogs; tweets; pseudo-relevance feedback; tweet retrieval; news websites.
International Journal of Web Science, 2012 Vol.1 No.4, pp.368 - 380
Available online: 07 Mar 2013 *Full-text access for editors Access for subscribers Purchase this article Comment on this article