User real-time interest prediction based on collaborative filtering and interactive computing for academic recommendation

Authors:
Jie Yu;Haihong Zhao;Fangfang Liu
Affiliations:
School of Computer Engineering and Science, Shanghai University, Shanghai, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China;School of Computer Engineering and Science, Shanghai University, Shanghai, China
Venue:
ICIC'12 Proceedings of the 8th international conference on Intelligent Computing Theories and Applications
Year:
2012

Citing 7
Cited 0

A Statistical Model for User Preference

IEEE Transactions on Knowledge and Data Engineering
Resume information extraction with cascaded hybrid model

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
The dynamics of interactive information retrieval behavior, Part I: An activity theory perspective

Journal of the American Society for Information Science and Technology
Evaluating Bayesian networks' precision for detecting students' learning styles

Computers & Education
Learning drifting concepts: Example selection vs. example weighting

Intelligent Data Analysis
A Combination Approach to Web User Profiling

ACM Transactions on Knowledge Discovery from Data (TKDD)
Empirical analysis of predictive algorithms for collaborative filtering

UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.