Algorithm of User Interest Drift Based on Matrix Representation

Article Preview

Abstract:

In order to improve the efficiency of user interest drift, proposed an algorithm of user interest drift based on matrix representation. Time Window was brought in to group short-time interest; Semantic Net was used to combine user interest categories; interest weight was replaced by interest rate to show the preference of user interest; considering the sustainability and volatility of interest to calculate the ultimate interest model. Experiment indicated, compared with previous method, this algorithm improved the accuracy of dealing with interest shift.

You might also be interested in these eBooks

Info:

Periodical:

Pages:

409-415

Citation:

Online since:

November 2010

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2011 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] Anthony Jameson, User Modeling Meets Usability Goals, Vol. 3538, Lecture Notes in Computer Science, pp.1-3, (2005).

Google Scholar

[2] Hong xiao Fei, Yi Dai, User Interest Drift Method based on Optimal Time Window,Computer Engineering, 34(16), (2008).

Google Scholar

[3] Cheng Y, Qiu G, Bu J, et al. Model Bloggers' Interests based on Forgetting Mechanism[C], Proceeding of the 17th International Conference on World Wide Web, WWW'08: 1129-1130, (2008).

DOI: 10.1145/1367497.1367690

Google Scholar

[4] Li L, Yang Z, Wang B et al. Dynamic Adaptation Strategies for Long-term and Short-term User Profile to Personalize Search [M]. Lecture Notes in Computer Science, APWeb/WAIM'07, LNCS 4505, 228-240, Berlin, (2007).

DOI: 10.1007/978-3-540-72524-4_26

Google Scholar

[5] Prasanna Ganesan, Hector Garcia- Molina, Jennifer Widom. Exploiting Hierarchical Domain Structure to Compute Similarity[J]. ACM Transactions on Information Systems, 21( 1): 64~93, (2003).

DOI: 10.1145/635484.635487

Google Scholar