Knowledge effects on document selection in search results pages

Authors:
Michael J. Cole;Xiangmin Zhang;Chang Liu;Nicholas J. Belkin;Jacek Gwizdka
Affiliations:
Rutgers, The State University of New Jersey, New Brunswick, NJ, USA;Wayne State University, Detroit, MI, USA;Rutgers, The State University of New Jersey, New Brunswick, NJ, USA;Rutgers, The State University of New Jersey, New Brunswick, NJ, USA;Rutgers, The State University of New Jersey, New Brunswick, NJ, USA
Venue:
Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval
Year:
2011

Citing 5
Cited 1

Evaluating the accuracy of implicit feedback from clicks and query reformulations in Web search

ACM Transactions on Information Systems (TOIS)
Information Foraging Theory: Adaptive Interaction with Information

Information Foraging Theory: Adaptive Interaction with Information
Characterizing the influence of domain expertise on web search behavior

Proceedings of the Second ACM International Conference on Web Search and Data Mining
Potential for personalization

ACM Transactions on Computer-Human Interaction (TOCHI)
A data analysis and modelling framework for the evaluation of interactive information retrieval

ECIR'2010 Proceedings of the 32nd European conference on Advances in Information Retrieval

Inferring user knowledge level from eye movement patterns

Information Processing and Management: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Click through events in search results pages (SERPs) are not reliable implicit indicators of document relevance. A user's task and domain knowledge are key factors in recognition and link selection and the most useful SERP document links may be those that best match the user's domain knowledge. User study participants rated their knowledge of genomics MeSH terms before conducting 2004 TREC Genomics Track tasks. Each participant's document knowledge was represented by their knowledge of the indexing MeSH terms. Results show high, intermediate, and low domain knowledge groups had similar document selection SERP rank distributions. SERP link selection distribution varied when participant knowledge of the available documents was analyzed. High domain knowledge participants usually selected a document with the highest personal knowledge rating. Low domain knowledge participants were reasonably successful at selecting available documents of which they had the most knowledge, while intermediate knowledge participants often failed to do so. This evidence for knowledge effects on SERP link selection may contribute to understanding the potential for personalization of search results ranking based on user domain knowledge.