Incorporating Social Information in Recommender Systems Using Hidden Markov Model

  • Jia-xin Zhang
  • Jin TianEmail author
Conference paper


User preference always changes over time, which makes time the strong context information in the recommender system. Many time-dependent recommender systems have been proposed to track the change of users’ preferences. However, the social factor, which has been proved useful for recommender systems, is rarely considered in these models. In this paper, we consider the effects of social friends on the users’ behavior and propose a dynamic recommender system based on the hidden Markov model to provide better recommendations for users. We compare the proposed model with the traditional static and dynamic recommendation methods on real datasets and the experimental results show that the proposed model outperforms the compared methods.


Recommender system Social information Hidden Markov model 



The work was supported by the General Program of the National Science Foundation of China (Grant No. 71471127, 71502125).


  1. 1.
    A. Tuzhilin, Towards the next generation of recommender systems, in Proceedings of the 1st International Conference on E-Business Intelligence (ICEBI2010), pp. 734–749Google Scholar
  2. 2.
    R.J. Mooney, L. Roy, Content-based book recommending using learning for text categorization, in Proceedings of the Fifth ACM Conference on Digital Libraries (2000), pp. 195–204Google Scholar
  3. 3.
    G. Guo, Integrating trust and similarity to ameliorate the data sparsity and cold start for recommender systems, in Proceedings of the 7th ACM conference on Recommender systems (RecSys’13) (2013), pp. 451–454Google Scholar
  4. 4.
    C. Chen, X. Zheng, Y. Wang, F. Hong, Z. Lin, Context-ware collaborative topic regression with social matrix factorization for recommender systems, in AAAI’14 Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence (2014), pp. 9–15Google Scholar
  5. 5.
    X. Ren, M. Song, E. Haihong, J. Song, Context-aware probabilistic matrix factorization modeling for point-of-interest recommendation. Neurocomputing 38–55 (2017)CrossRefGoogle Scholar
  6. 6.
    Y. Koren, Collaborative filtering with temporal dynamics. Commun. ACM 53(4), 89–97 (2010)CrossRefGoogle Scholar
  7. 7.
    H. Bao, Q. Li, S.S. Liao, S. Song, H. Gao, A new temporal and social PMF-based method to predict users’ interests in micro-blogging. Decis. Support Syst. 55(3), 698–709 (2013)CrossRefGoogle Scholar
  8. 8.
    L. Xiang et al., Temporal recommendation on graphs via long- and short-term preference fusion, in ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2010), pp. 723–732Google Scholar
  9. 9.
    K. Inuzuka, T. Hayashi, T. Takagi, Recommendation system based on prediction of user preference changes, in International Conference on Web Intelligence (2017), pp. 192–199Google Scholar
  10. 10.
    M. Hosseinzadeh Aghdam et al., Adapting recommendations to contextual changes using hierarchical hidden markov models, in Proceedings of the 9th ACM Conference on Recommender Systems (2015), pp. 241–244Google Scholar
  11. 11.
    L.E. Baum, Statistical inference for probabilistic functions of finite Markov chains. Ann. Math. Stat. 37(6), 1554–1563 (1966)Google Scholar
  12. 12.
    N. Sahoo, P.V. Singh, T. Mukhopadhyay, A hidden Markov model for collaborative filtering. Manage. Inf. Syst. Q. 36(4), 1329–1356 (2012)CrossRefGoogle Scholar
  13. 13.
    A.P. Dempster, Maximum likelihood from incomplete data via EM algorithm. J. R. Stat. Soc. B 39, 1–38 (1977)Google Scholar
  14. 14.
    T. Hofmann, J. Puzicha, Latent class models for collaborative filtering, in Sixteenth International Joint Conference on Artificial Intelligence (1990), pp. 688–693Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.College of Management and EconomicsTianjin UniversityTianjinChina

Personalised recommendations