Collaborative Filtering Model Based on Time Context for IPTV Live Recommendation

  • Zhengying Hu
  • Yun Gao
  • Xin WeiEmail author
  • Fang Zhou
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 834)


With the increase in the number of IPTV live channels, the users are faced with the problem of information overload and the degraded users’ quality of experience (QoE). This paper combines the time context information with the collaborative filtering recommendation algorithm to design the IPTV live recommendation system (RS). Finally, the fusion recommendation model is proposed and its accuracy rate has a great improvement.


Live recommendation system Time context Collaborative filtering Fusion model 



This work is partly supported by the National Natural Science Foundation of China (Grants No. 61571240, 61671474), the Jiangsu Science Fund for Excellent Young Scholars (No. BK20170089), the ZTE program ‘‘The Prediction of Wireline Network Malfunction and Traffic Based on Big Data’’ and the Priority Academic Program Development of Jiangsu Higher Education Institutions.


  1. 1.
    Yu, C., Ding, H., Cao, H., Liu, Y., Yang, C.: Follow me: personalized IPTV channel switching guide. In: Proceedings of the 8th ACM on Multimedia Systems Conference, pp. 147–157. ACM, Taipei, Taiwan (2017)Google Scholar
  2. 2.
    Kwon, O.B.: “I know what you need to buy”: context-aware multimedia-based recommendation system. Expert Syst. Appl. 25(3), 387–400 (2003)CrossRefGoogle Scholar
  3. 3.
    Prota, T., Bispo, A., Ferraz, C.: A literature review of recommender systems in the television domain. Expert Syst. Appl. 42(22), 9046–9076 (2015)CrossRefGoogle Scholar
  4. 4.
    Zhou, L., Wu, D., Dong, Z., Li, X.: When collaboration hugs intelligence: content delivery over ultra-dense network. IEEE Commun. Mag. 55(12), 91–95 (2017)CrossRefGoogle Scholar
  5. 5.
    Zhou, L., Wu, D., Chen, J., Dong, Z.: Greening the smart cities: energy-efficient massive content delivery via D2D communications. IEEE Trans. Ind. Inf. 14(4), 1626–1634 (2017)CrossRefGoogle Scholar
  6. 6.
    Xijun, Y.E., Gong, Y.: Study on diversity of collaborative filtering recommendation algorithm based on item category. Comput. Eng. 41(10), 42–46 (2015)Google Scholar
  7. 7.
    Wu D., Zhou L., Cai Y.M., Qian Yi.: Collaborative caching and matching for D2D content sharing. IEEE Wirel. Commun. Mag. 25(3), 43–49 (2018)CrossRefGoogle Scholar
  8. 8.
    Deshpande, M., Karypis, G.: Item-based top-N recommendation algorithm. ACM Trans. Inf. Syst. 22(1), 143–177 (2004)CrossRefGoogle Scholar
  9. 9.
    Lee, S.I., Lee, S.Y.: Integration of user profiles and real-time context information reflecting time-based changes for the recommendation system. Int. J. Fuzzy Logic Intell. Syst. 8(4), 270–275 (2008)CrossRefGoogle Scholar
  10. 10.
    Hu, L., Song, G., Xie, Z., Zhao, K.: Personalized recommendation algorithm based on preference features. Tsinghua Sci. Technol. 19(3), 293–299 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.College of Telecommunications and Information Engineering, Nanjing University of Posts and TelecommunicationsNanjingChina
  2. 2.National Engineering Research Center for Communication and Information Technology (NUPT)NanjingChina
  3. 3.School of Electrical and Information EngineeringAnhui University of TechnologyMaanshanChina

Personalised recommendations