Predicting user interests from contextual information

ABSTRACT

Search and recommendation systems must include contextual information to effectively model users' interests. In this paper, we present a systematic study of the effectiveness of five variant sources of contextual information for user interest modeling. Post-query navigation and general browsing behaviors far outweigh direct search engine interaction as an information-gathering activity. Therefore we conducted this study with a focus on Website recommendations rather than search results. The five contextual information sources used are: social, historic, task, collection, and user interaction. We evaluate the utility of these sources, and overlaps between them, based on how effectively they predict users' future interests. Our findings demonstrate that the sources perform differently depending on the duration of the time window used for future prediction, and that context overlap outperforms any isolated source. Designers of Website suggestion systems can use our findings to provide improved support for post-query navigation and general browsing behaviors.

REFERENCES

• 1: Eugene Agichtein , Eric Brill , Susan Dumais, Improving web search ranking by incorporating user behavior information, Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, August 06-11, 2006, Seattle, Washington, USA [doi>10.1145/1148170.1148177]
• 2: Mikhail Bilenko , Ryen W. White , Matthew Richardson , G. Craig Murray, Talking the talk vs. walking the walk: salience of information needs in querying vs. browsing, Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval, July 20-24, 2008, Singapore, Singapore [doi>10.1145/1390334.1390461]
• 3: Andrei Broder, A taxonomy of web search, ACM SIGIR Forum, v.36 n.2, Fall 2002 [doi>10.1145/792550.792552]
• 4: Budzik, J.&Hammond, K. (1999). Watson: anticipating and contextualizing information needs. Proc. ASIS, 727--740.
• 5: Katriina Byström , Kalervo Järvelin, Task complexity affects information seeking and use, Information Processing and Management: an International Journal, v.31 n.2, p.191-213, March/April 1995 [doi>10.1016/0306-4573(94)00041-Z]
• 6: Abdur Chowdhury , Ian Soboroff, Automatic evaluation of world wide web search services, Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, August 11-15, 2002, Tampere, Finland [doi>10.1145/564376.564474]
• 7: Mark Claypool , David Brown , Phong Le , Makoto Waseda, Inferring User Interest, IEEE Internet Computing, v.5 n.6, p.32-39, November 2001 [doi>10.1109/4236.968829]
• 8: Dupret, G., Murdock, V.&Piwowarski, B. (2007). Web search evaluation using clickthrough data and a user model. Proc. WWW Workshop on Query Log Analysis.
• 9: David Goldberg , David Nichols , Brian M. Oki , Douglas Terry, Using collaborative filtering to weave an information tapestry, Communications of the ACM, v.35 n.12, p.61-70, Dec. 1992 [doi>10.1145/138859.138867]
• 10: Gunduz, S.U.&ÖÖzsu, M.T., (2003). Recommendation models for user accesses to web pages. Proc. Conf. on Artificial Neural Networks, 1003--1010.
• 11: Peter Ingwersen, Polyrepresentation of information needs and semantic entities: elements of a cognitive theory for information retrieval interaction, Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval, p.101-110, July 03-06, 1994, Dublin, Ireland
• 12: Peter Ingwersen , Kalervo Järvelin, The Turn: Integration of Information Seeking and Retrieval in Context (The Information Retrieval Series), Springer-Verlag New York, Inc., Secaucus, NJ, 2005
• 13: Kalervo Järvelin , Jaana Kekäläinen, IR evaluation methods for retrieving highly relevant documents, Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, p.41-48, July 24-28, 2000, Athens, Greece [doi>10.1145/345508.345545]
• 14: Thorsten Joachims , Filip Radlinski, Search Engines that Learn from Implicit Feedback, Computer, v.40 n.8, p.34-40, August 2007 [doi>10.1109/MC.2007.289]
• 15: Melanie Kellar , Carolyn Watters , Michael Shepherd, A field study characterizing Web-based information-seeking tasks, Journal of the American Society for Information Science and Technology, v.58 n.7, p.999-1018, May 2007 [doi>10.1002/asi.v58:7]
• 16: Diane Kelly , Vijay Deepak Dollu , Xin Fu, The loquacious user: a document-independent source of terms for query expansion, Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval, August 15-19, 2005, Salvador, Brazil [doi>10.1145/1076034.1076112]
• 17: Faten Khalil , Jiuyong Li , Hua Wang, Integrating recommendation models for improved web page prediction accuracy, Proceedings of the thirty-first Australasian conference on Computer science, January 01-01, 2008, Wollongong, Australia
• 18: Kyung-Sun Kim , Bryce Allen, Cognitive and task influences on Web searching behavior, Journal of the American Society for Information Science and Technology, v.53 n.2, p.109-119, January 15, 2002 [doi>10.1002/asi.10014]
• 19: Birger Larsen , Peter Ingwersen, The boomerang effect: retrieving scientific documents via the network of references and citations, Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, August 11-15, 2002, Tampere, Finland [doi>10.1145/564376.564462]
• 20: Ying Li , Zijian Zheng , Honghua (Kathy) Dai, KDD CUP-2005 report: facing a great challenge, ACM SIGKDD Explorations Newsletter, v.7 n.2, p.91-99, December 2005 [doi>10.1145/1117454.1117466]
• 21: Lieberman, H. (1995). Letizia: an agent that assists web browsing. Proc. IJCAI, 924--929.
• 22: Oard, D.&Kim, J. (1998). Implicit feedback for recommender systems. Proc. AAAI Wkp. on Rec. Sys., 81--83.
• 23: James Pitkow , Hinrich Schütze , Todd Cass , Rob Cooley , Don Turnbull , Andy Edmonds , Eytan Adar , Thomas Breuel, Personalized search, Communications of the ACM, v.45 n.9, September 2002 [doi>10.1145/567498.567526]
• 24: Benjamin Piwowarski , Hugo Zaragoza, Predictive user click models based on click-through history, Proceedings of the sixteenth ACM conference on Conference on information and knowledge management, November 06-10, 2007, Lisbon, Portugal [doi>10.1145/1321440.1321467]
• 25: Feng Qiu , Junghoo Cho, Automatic identification of user interest for personalized search, Proceedings of the 15th international conference on World Wide Web, May 23-26, 2006, Edinburgh, Scotland [doi>10.1145/1135777.1135883]
• 26: Xuehua Shen , Susan Dumais , Eric Horvitz, Analysis of topic dynamics in web search, Special interest tracks and posters of the 14th international conference on World Wide Web, May 10-14, 2005, Chiba, Japan [doi>10.1145/1062745.1062889]
• 27: Xuehua Shen , Bin Tan , ChengXiang Zhai, Context-sensitive information retrieval using implicit feedback, Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval, August 15-19, 2005, Salvador, Brazil [doi>10.1145/1076034.1076045]
• 28: Singhal, A. (2001). Modern information retrieval: A brief overview. IEEE Data Engineering Bulletin, 24(4), 35--43.
• 29: Mette Skov , Birger Larsen , Peter Ingwersen, Inter and intra-document contexts applied in polyrepresentation, Proceedings of the 1st international conference on Information interaction in context, October 18-20, 2006, Copenhagen, Denmark [doi>10.1145/1164820.1164841]
• 30: Bin Tan , Xuehua Shen , ChengXiang Zhai, Mining long-term search history to improve search accuracy, Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, August 20-23, 2006, Philadelphia, PA, USA [doi>10.1145/1150402.1150493]
• 31: Jaime Teevan , Susan T. Dumais , Eric Horvitz, Personalizing search via automated analysis of interests and activities, Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval, August 15-19, 2005, Salvador, Brazil [doi>10.1145/1076034.1076111]
• 32: Hitoshi Terai , Hitomi Saito , Yuka Egusa , Masao Takaku , Makiko Miwa , Noriko Kando, Differences between informational and transactional tasks in information seeking on the web, Proceedings of the second international symposium on Information interaction in context, October 14-17, 2008, London, United Kingdom [doi>10.1145/1414694.1414728]
• 33: Andrew Thatcher, Web search strategies: The influence of Web experience and task type, Information Processing and Management: an International Journal, v.44 n.3, p.1308-1329, May, 2008 [doi>10.1016/j.ipm.2007.09.004]
• 34: Ryen W. White , Steven M. Drucker, Investigating behavioral variability in web search, Proceedings of the 16th international conference on World Wide Web, May 08-12, 2007, Banff, Alberta, Canada [doi>10.1145/1242572.1242576]
• 35: Ryen W. White , Susan T. Dumais , Jaime Teevan, Characterizing the influence of domain expertise on web search behavior, Proceedings of the Second ACM International Conference on Web Search and Data Mining, February 09-12, 2009, Barcelona, Spain [doi>10.1145/1498759.1498819]
• 36: Ryen W. White , Ian Ruthven , Joemon M. Jose, A study of factors affecting the utility of implicit relevance feedback, Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval, August 15-19, 2005, Salvador, Brazil [doi>10.1145/1076034.1076044]
• 37: Yi Zhang , Jonathan Koren, Efficient bayesian hierarchical user modeling for recommendation system, Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, July 23-27, 2007, Amsterdam, The Netherlands [doi>10.1145/1277741.1277752]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Search process

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Information filtering

General Terms:
Algorithms, Experimentation, Human Factors

Keywords:
context, user interest modeling, website recommendation