Interaction Model to Predict Subjective-Specificity of Search Results

Exploratory search is becoming more common as the web is used more increasingly as a medium for learning and discovery. Compared to traditional known-item search, exploratory search is more challenging and difficult to support because it initiates with poorly defined search goals, while the user knowledge and information needs constantly change throughout the search process. Modeling the user behavior in exploratory search is a hard problem to solve. In spite of a large amount of research on personalization, little attention has been devoted to personalization in the context of exploratory search taking into account the evolving information needs of the user. We propose a formal model— motivated by Information Foraging Theory—for predicting specificity of search results with respect to the evolving knowledge and information needs of the user in exploratory search.

[1]  Jacek Gwizdka,et al.  Inferring user knowledge level from eye movement patterns , 2013, Inf. Process. Manag..

[2]  Kevin Li,et al.  Faceted metadata for image search and browsing , 2003, CHI '03.

[3]  Thorsten Joachims,et al.  Optimizing search engines using clickthrough data , 2002, KDD.

[4]  Xin Fu,et al.  Elicitation of term relevance feedback: an investigation of term source and context , 2006, SIGIR.

[5]  Mark S. Ackerman,et al.  The perfect search engine is not enough: a study of orienteering behavior in directed search , 2004, CHI.

[6]  Stuart K. Card,et al.  Information foraging in information access environments , 1995, CHI '95.

[7]  Mika Käki,et al.  Findex: search result categories help users when document ranking fails , 2005, CHI.

[8]  Peter Bailey,et al.  Understanding the relationship of information need specificity to search query length , 2007, SIGIR.

[9]  Gary Marchionini,et al.  Exploratory search , 2006, Commun. ACM.

[10]  Dorota Glowacka,et al.  Directing exploratory search: reinforcement learning from user interactions with keywords , 2013, IUI '13.

[11]  Aniket Kittur,et al.  Apolo: making sense of large network data by combining rich user interaction and machine learning , 2011, CHI.

[12]  Paolo Ferragina,et al.  A personalized search engine based on Web‐snippet hierarchical clustering , 2008, Softw. Pract. Exp..

[13]  Eve E. Hoggan,et al.  Information-seeking behaviors of computer scientists: Challenges for electronic literature search tools , 2013, ASIST.

[14]  Ryen W. White,et al.  Supporting exploratory search , 2006 .