A User-Oriented Webpage Ranking Algorithm Based on User Attention Time

We propose a new webpage ranking algorithm which is personalized. Our idea is to rely on the attention time spent on a document by the user as the essential clue for producing the user-oriented webpage ranking. The prediction of the attention time of a new webpage is based on the attention time of other previously browsed pages by this user. To acquire the attention time of the latter webpages, we developed a browser plugin which is able to record the time a user spends reading a certain webpage and then automatically send that data to a server. Once the user attention time is acquired, we calibrate it to account for potential repetitive occurrences of the webpage before using it in the prediction process. After the user's attention times of a collection of documents are known, our algorithm can predict the user's attention time of a new document through document content similarity analysis, which is applied to both texts and images. We evaluate the webpage ranking results from our algorithm by comparing them with the ones produced by Google's Pagerank algorithm.

[1]  Miroslav Kubat,et al.  Time spent on a web page is sufficient to infer a user's interest , 2007 .

[2]  Hinrich Schütze,et al.  Personalized search , 2002, CACM.

[3]  Steve Fox,et al.  Evaluating implicit measures to improve web search , 2005, TOIS.

[4]  Ji-Rong Wen,et al.  A large-scale evaluation and analysis of personalized search strategies , 2007, WWW '07.

[5]  Thorsten Joachims,et al.  Eye-tracking analysis of user behavior in WWW search , 2004, SIGIR '04.

[6]  A. Bernstein,et al.  SimPack: A Generic Java Library for Similarity Measures in Ontologies , 2005 .

[7]  Chris Buckley,et al.  OHSUMED: an interactive retrieval evaluation and new large test collection for research , 1994, SIGIR '94.

[8]  Joydeep Ghosh,et al.  Value-based customer grouping from large retail data sets , 2000, SPIE Defense + Commercial Sensing.

[9]  Nicholas J. Belkin,et al.  Display time as implicit feedback: understanding task effects , 2004, SIGIR '04.

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

[11]  Huan Liu,et al.  CubeSVD: a novel approach to personalized Web search , 2005, WWW '05.

[12]  Nicholas J. Belkin,et al.  Reading time, scrolling and interaction: exploring implicit sources of user preferences for relevance feedback , 2001, Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.

[13]  Filip Radlinski,et al.  Query chains: learning to rank from implicit feedback , 2005, KDD '05.

[14]  Xin Fu,et al.  Evaluating sources of implicit feedback in web searches , 2007, RecSys '07.

[15]  Edward Cutrell,et al.  An eye tracking study of the effect of target rank on web search , 2007, CHI.

[16]  Ryen W. White,et al.  The Use of Implicit Evidence for Relevance Feedback in Web Retrieval , 2002, ECIR.

[17]  Klaus R. Dittrich,et al.  Generic similarity detection in ontologies with the SOQA-SimPack toolkit , 2006, SIGMOD Conference.

[18]  Thorsten Joachims,et al.  Accurately interpreting clickthrough data as implicit feedback , 2005, SIGIR '05.

[19]  Gerard Salton,et al.  Improving retrieval performance by relevance feedback , 1997, J. Am. Soc. Inf. Sci..

[20]  Benjamin Piwowarski,et al.  Web Search Engine Evaluation Using Clickthrough Data and a User Model , 2007 .

[21]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Ryen W. White,et al.  Comparing Explicit and Implicit Feedback Techniques for Web Retrieval: TREC-10 Interactive Track Report , 2001, TREC.

[23]  Zhi-Hua Zhou,et al.  Exploiting Image Contents in Web Search , 2007, IJCAI.