Comparing Two Strategies for Query Expansion in a News Monitoring System
In this paper, we study query expansion strategies that improve the relevance of retrieved documents in a news and social media monitoring system, which performs real-time searches based on complex queries. We propose a two-step retrieval strategy using textual features such as bi-gram word dependencies, proximity, and expansion terms. We compare two different methods for query expansion: (1) based on word co-occurrence information; (2) using semantically-related expansion terms. We evaluate our methods and compare them with the baseline version of the system by crowdsourcing user-centric tasks. The results show that word co-occurrence outperforms semantic query expansion, and improves over the baseline in terms of relevance and utility.
KeywordsQuery analysis Query expansion Web IR and social media search
This work was funded by the Swiss Commission for Technology and Innovation.
- 1.Arguello, J., Diaz, F., Callan, J., Crespo, J.: Sources of evidence for vertical selection. In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 315–322 (2009)Google Scholar
- 2.Cao, G., Nie, J., Gao, J., Robertson, S.: Selecting good expansion terms for pseudo-relevance feedback. In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 243–250 (2008)Google Scholar
- 4.Habibi, M., Popescu-Belis, A.: Using crowdsourcing to compare document recommendation strategies for conversations. In: Workshop on Recommendation Utility Evaluation, Held in Conjunction with ACM RecSys (2012)Google Scholar
- 6.Ponte, J.M., Croft, B.: A language modeling approach to information retrieval.In: Proceedings of ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 275–281 (1998)Google Scholar
- 8.Zhao, L., Callan, J.: Term necessity prediction. In: Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM), pp. 259–268 (2010)Google Scholar