Investigating Query Reformulation Behavior of Search Users

Search engine users usually strive to reformulate their queries in the search process to gain useful information. It is hard for search engines to understand users’ search intents and return appropriate results if they submit improper or ambiguous queries. Therefore, query reformulation is a bottleneck issue in the usability of search engines. Modern search engines normally provide users with some query suggestions for references. To help users to better learn their information needs, it is of vital importance to investigate users’ reformulation behaviors thoroughly. In this paper, we conduct a detailed investigation of users’ session-level reformulation behavior on a large-scale session dataset and discover some interesting findings that previous work may not notice before: (1) Intent ambiguity may be the direct cause of long sessions rather than the complexity of users’ information needs; (2) Both the added and the deleted terms in a reformulation step can be influenced by the clicked results to a greater extent than the skipped ones; (3) Users’ specification actions are more likely to be inspired by the result snippets or the landing pages, while the generalization behaviors are impacted largely by the result titles. We further discuss some concerns about the existing query suggestion task and give some suggestions on the potential research questions for future work. We hope that this work could provide assistance for the researchers who are interested in the relative domain.

[1]  Byron J. Gao,et al.  Utilizing User-input Contextual Terms for Query Disambiguation , 2010, COLING.

[2]  Ziv Bar-Yossef,et al.  Context-sensitive query auto-completion , 2011, WWW.

[3]  Jakob Grue Simonsen,et al.  A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion , 2015, CIKM.

[4]  Milad Shokouhi,et al.  Query Suggestion and Data Fusion in Contextual Disambiguation , 2015, WWW.

[5]  Maarten de Rijke,et al.  Personalized Query Suggestion Diversification , 2017, SIGIR.

[6]  Yiqun Liu,et al.  How do users describe their information need: Query recommendation based on snippet click model , 2011, Expert Syst. Appl..

[7]  Yiqun Liu,et al.  Hierarchical Attention Network for Context-Aware Query Suggestion , 2018, AIRS.

[8]  Daniel Gayo-Avello,et al.  Stratified analysis of AOL query log , 2009, Inf. Sci..

[9]  W. Bruce Croft,et al.  Query reformulation using anchor text , 2010, WSDM '10.

[10]  Zhiyuan Liu,et al.  Query Suggestion with Feedback Memory Network , 2018, WWW.

[11]  Sebastian Dungs,et al.  An Eye-Tracking Study of Query Reformulation , 2015, SIGIR.

[12]  Yen-Jen Oyang,et al.  Relevant term suggestion in interactive web search based on contextual information in query session logs , 2003, J. Assoc. Inf. Sci. Technol..

[13]  Pu-Jen Cheng,et al.  Learning user reformulation behavior for query auto-completion , 2014, SIGIR.

[14]  Phivos Mylonas,et al.  Semantic query suggestion using Twitter Entities , 2015, Neurocomputing.

[15]  Enrique Alfonseca,et al.  Learning to Attend, Copy, and Generate for Session-Based Query Suggestion , 2017, CIKM.

[16]  Enhong Chen,et al.  Context-aware query suggestion by mining click-through and session data , 2008, KDD.

[17]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[18]  Wei Wang,et al.  RIN: Reformulation Inference Network for Context-Aware Query Suggestion , 2018, CIKM.

[19]  Qi He,et al.  Web Query Recommendation via Sequential Query Prediction , 2009, 2009 IEEE 25th International Conference on Data Engineering.

[20]  Yang Song,et al.  Post-ranking query suggestion by diversifying search results , 2011, SIGIR '11.