Study on Personalized Recommendation Technology of Digital TV Programs

Abstract:

This paper aims at one of key technologies in digital television development ---intelligent personalized recommendation technology of digital TV programs for study. This paper proposes to take advantage of ample TV-Anytime to describe metadata so as to perform specific plans of guide service for TV programs based on TV-Anytime metadata specification. It combines technology such as data mining and artificial intelligence etc with a view of building a personalized TV program recommendation system on the framework of the multi-agent. Besides, a hybrid algorithm with content filtering and collaborative filtering based on the systematical recommendation algorithm has been put forward. In order to overcome the deficiencies of traditional collaborative filtering algorithm which relies on users explicit evaluation, the paper represents an improved algorithm with the footing of content collaborative filtering.

• Periodical: Applied Mechanics and Materials (Volumes 347-350)
• Pages: 3035-3038
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.347-350.3035
• Online since: August 2013
• Authors: Xiao Bin Wang, Qing Jun Wang
• Keywords: Collaborative Filtering Algorithm, Digital TV, Recommendation Technology

References

[1] Liu Yunyi. Literature recommendation system based on users' preference [J], Information Theory and Practice, 2007, 30 (1): 61-64.

[2] Guo Liang. An improved the algorithm-FP_MAXMN algorithm in personalized bibliographic recommended system [J], Fujian computer, 2008, 8: 100-101.

[3] Zhang Peiping. Personalized web recommended system on web content and log mining [J] Computer System Applications-11, 2008, 9: 9.

[4] Zhang Peiying. Personalized web recommended system on fuzzy membership degree [J] Computer System Applications-13, 2008, 11: 11.

[5] Sarwar B, Karypis G, Konstan J, Riedl J. Item based ColIaborative Filtering Recommendation Algorithms. International world wide web conrerence. 2001. 10.

DOI: 10.1145/371920.372071

[6] Franca Debole, Fabrizio Sebastiani. Supervised Term Weighting for Automated Text Categorization. Proceedings of the 2003 ACM Symposium on Applied Computing, 2003: 784-788.

DOI: 10.1145/952532.952688

[7] Man Lan, Chew Lim Tan, Hwee-Boon Low, Sam Yuan Sung. A comprehensive comparative study on term weighting schemes for text categorization with support vector machines. WWW (Special interest tracks and posters), 2005: 1032-1033.

DOI: 10.1145/1062745.1062854

[8] Wei-poe Lee, Jian-Hsin wang. A user Centered Remote Control System for personalized Multimedia Channel Selection. IEEE Trans. on Consumer Electronics，2004. 10. 50(4): 1009-1015.

DOI: 10.1109/tce.2004.1362492

[9] Scholkopf B. Smola A.J. Williamson R.C. et al. New Support Vector Algorithms[J]. Neural Computation, 2000(12): 120-156.

[10] Dagan I., Lee L., Pereira F. Similarity-based models of word cooccurrence probabilities. Machine Learning, Special issue on Machine Learning and Natural Language, 1999, 34(1-3): 43-69.

[11] Zhiwe Yu, Xingshe Zhou. TV3P : An Adaptive Assistant for PersonaliZed TV. IEEE Trans. on Consumer Electronics. 2004. 1. 50(1).

DOI: 10.1109/tce.2004.1277889

[12] Wei-po Lee, Tsung-Hsien yang. Persona1izing Information Appliances: a Multi-agent Framework for TV Programme Recommendations. Expert systems with Application. 2003: 331-341.

DOI: 10.1016/s0957-4174(03)00074-5