User Real-Time Interest Prediction Based on Collaborative Filtering and Interactive Computing for Academic Recommendation
With rapid development of Internet, information and resource of Web academic database is great and explosive growth, so it is difficult to quickly and accurately obtain information which meets individual user’s needs. Web personalized services can effectively solve the problem of information overload problem and alleviate user’s cognitive burden. How to predict user interest is a key issue in Web personalized services. First, this paper proposes concepts of user knowledge unit and user knowledge flow that represents user short-term interest and long-term interest respectively. Second, existing methods have some defects which can’t be sensitive to perceive user interest change and accurately predict user real-time interest; we put forward Collaborative Time Weight (CTW) and Collaborative Relation Weight (CRW) to solve those problems. Meanwhile the prediction algorithm for user real-time interest is proposed based on collaborative filtering and interactive computing. Finally, experimental results demonstrate that our method can capture user real-time interests accurately and alleviate the user’s cognitive burden effectively.
KeywordsWeb personalization services User knowledge flow Interactive computing Collaborative filtering User interest prediction
Unable to display preview. Download preview PDF.
- 1.Guang, Y.K., Zhou, M.: Resume information extraction with cascaded hybrid model. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics (ACL), pp. 499–506 (2005)Google Scholar
- 2.Tang, J., Zhang, D., Yao, L.: A Combination approach to web user profiling. Knowledge Discovery from Data 5(1), Article 2 (2010)Google Scholar
- 3.Jung, S.Y., Hong, J.H., Kim, T.S.: A Statistical Model for User Preference. Knowledge and Data Engineering 17(6) (2005)Google Scholar
- 4.Sugiyama, K., Hatano, K., Yoshikawa, M.: Adaptive Web Search Based on User Profile Constructed without Any Effort from Users, May 17–22. ACM, New York (2004), 1-58113-844-X/04/0005Google Scholar
- 6.Nkenberg, K.L.: Learning drifting concep: example selection vs example weighting. Intelligent Data Analysis 8(3), 281–300 (2004)Google Scholar
- 7.Oychev, K., Schwab, I.: Adaptation to drifting user’s intersects. In: Proceedings of ECML 392 45 (2000)Google Scholar
- 11.Piwowarski, B., Lalmas, M.: A Quantum-based Model for Interactive Information Retrieval (extended version). ArXiv e-prints (0906.4026) (2009) Google Scholar
- 12.Breese, J.S., Heckerman, D., Kadie, C.: Empirical Analysis of Predictive Algorithm for Collaborative Filtering. In: Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence, pp. 43–52 (1998)Google Scholar
- 13.Nissen, M.E.: An Extended Model of Knowledge Flow Dynamics. Communications of the Association for Information Systems, 251–266 (2002)Google Scholar
- 14.Yu, J., Liu, F.F., Gong, J.: Discovering Collaborative Users based on Query Context for Web Information Seeking. In: Proceedings of the 2th International Conference on Future Computer and Communication (2010)Google Scholar
- 15.Yu, J., Liu, F.F., Zhao, H.H.: Building User Profile based on Concept and Relation for Web Personalized Services. In: International Conference on Innovation and Information Management (2012)Google Scholar