Abstract
Incorporating the social network information into recommender systems has been demonstrated as an effective approach in improving the recommendation performance. When predicting ratings for an active user, his/her taste is influenced by the ones of his/her friends. Intuitively, different friends have different influential power to the active user. Most existing social recommendation algorithms, however, fail to consider such differences, and unfairly treat them equally. The problem is that the friends with less influential power might mislead the rating predictions, and finally impair the recommendation performance. Some previous work has tried to differentiate the influential power by local similarity calculations, but it has not provided a systematic solution and it has ignored the propagation of the influence among the social network. To solve the above limitations, in this paper, we investigate the issue of distinguishing different users’ influence power in recommendation systematically. We propose to employ three graph-based algorithms (including PageRank, HITS, and heat diffusion) to distinguish and propagate the influence among the friends of an active user, and then integrate them into the factorization-based social recommendation framework. Through experimental verification in the Epinions dataset, we demonstrate that the proposed approaches consistently outperform previous social recommendation algorithms significantly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Brin, S., Page, L.: The Anatomy of a Large-Scale Hypertextual Web Search Engine. Computer Networks and ISDN Systems J. 30, 107–117 (1998)
Canny, J.: Collaborative Filtering with Privacy via Factor Analysis. In: Proceedings of SIGIR 2002, pp. 238–245. ACM Press, New York (2002)
Chakrabarti, S., Dom, B., Gibson, D., Kleinberg, J., Raghavan, P., Rajagopalan, S.: Automatic Resource Compilation by Analyzing Hyperlink Structure and Associated Text. Computer Networks and ISDN Systems 30(1), 65–74 (1998)
Kleinberg, J.: Authoritative sources in a hyperlinked environment. In: 9th ACM-SIAM Symposium on Discrete Algorithms, pp. 604–632. ACM Press, New York (2008)
Linden, G., Smith, B., York, J.: Amazon.com Recommendations: Item-to-item Collaborative Filtering. IEEE Internet Computing J. 7(1), 76–80 (2003)
Ma, H., King, I., Lyu, M.R.: Effective Missing Data Prediction for Collaborative Filtering. In: Proceedings of SIGIR 2007, pp. 39–46. ACM Press, New York (2007)
Ma, H., Yang, H.X., Lyu, M.R., King, I.: Mining Social Networks Using Heat Diffusion Processes for Marketing Candidates Selection. In: Proceedings of CIKM 2008, pp. 233–242. ACM Press, Napa Valley (2008)
Ma, H., Yang, H., Lyu, M.R., King, I.: SoRec: Social Recommendation Using Probabilistic Matrix Factorization. In: Proceedings of CIKM 2008, pp. 931–940. ACM Press, New York (2008)
Ma, H., King, I., Lyu, M.R.: Learning to Recommend with Social Trust Ensemble. In: Proceedings of SIGIR 2009, pp. 203–210. ACM Press, Boston (2009)
Ma, H., Zhou, D.Y., Liu, C.: Recommender System with Social Regularization. In: Proceedings of WSDM 2011, pp. 287–296. ACM Press, Hong Kong (2011)
Xin, X., King, I., Deng, H., Lyu, M.R.: A social recommendation framework based on multi-scale continuous conditional random fields. In: Proceedings of CIKM 2009, pp. 1247–1256. ACM Press, Hong Kong (2009)
Xing, W., Ghorbani, A.: Weighted Pagerank Algorithm. In: 2nd Annual Conference on Communication Networks and Services Research, pp. 305–314. IEEE Press, Fredericton (2004)
Yang, H., King, I., Lyu, M.R.: Diffusionrank: a possible penicillin for web spamming. In: Proceedings of SIGIR 2007, pp. 431–438. ACM Press, Amsterdam (2007)
Zhang, Y., Koren, J.: Efficient Bayesian Hierarchial User Modeling for Recommendation System. In: Proceedings of SIGIR 2002, pp. 47–54. ACM Press, New York (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wei, X., Huang, H., Xin, X., Yang, X. (2013). Distinguishing Social Ties in Recommender Systems by Graph-Based Algorithms. In: Lin, X., Manolopoulos, Y., Srivastava, D., Huang, G. (eds) Web Information Systems Engineering – WISE 2013. WISE 2013. Lecture Notes in Computer Science, vol 8180. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41230-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-41230-1_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41229-5
Online ISBN: 978-3-642-41230-1
eBook Packages: Computer ScienceComputer Science (R0)