Microblog Retrieval Using Ensemble of Feature Sets through Supervised Feature Selection

Abu Nowshed CHY  Md Zia ULLAH  Masaki AONO  

IEICE TRANSACTIONS on Information and Systems   Vol.E100-D   No.4   pp.793-806
Publication Date: 2017/04/01
Publicized: 2017/01/17
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2016DAP0032
Type of Manuscript: Special Section PAPER (Special Section on Data Engineering and Information Management)
microblog search,  temporal information retrieval,  query expansion,  feature selection,  learning to rank,  time-aware ranking,  

Full Text: PDF>>
Buy this Article

Microblog, especially twitter, has become an integral part of our daily life for searching latest news and events information. Due to the short length characteristics of tweets and frequent use of unconventional abbreviations, content-relevance based search cannot satisfy user's information need. Recent research has shown that considering temporal and contextual aspects in this regard has improved the retrieval performance significantly. In this paper, we focus on microblog retrieval, emphasizing the alleviation of the vocabulary mismatch, and the leverage of the temporal (e.g., recency and burst nature) and contextual characteristics of tweets. To address the temporal and contextual aspect of tweets, we propose new features based on query-tweet time, word embedding, and query-tweet sentiment correlation. We also introduce some popularity features to estimate the importance of a tweet. A three-stage query expansion technique is applied to improve the relevancy of tweets. Moreover, to determine the temporal and sentiment sensitivity of a query, we introduce query type determination techniques. After supervised feature selection, we apply random forest as a feature ranking method to estimate the importance of selected features. Then, we make use of ensemble of learning to rank (L2R) framework to estimate the relevance of query-tweet pair. We conducted experiments on TREC Microblog 2011 and 2012 test collections over the TREC Tweets2011 corpus. Experimental results demonstrate the effectiveness of our method over the baseline and known related works in terms of precision at 30 (P@30), mean average precision (MAP), normalized discounted cumulative gain at 30 (NDCG@30), and R-precision (R-Prec) metrics.