Personalized Context-Aware Collaborative Filtering Based on Neural Network and Slope One

  • Min Gao
  • Zhongfu Wu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5738)


Currently, context has been identified as an important factor in recommender systems. Lots of researches have been done for context-aware collaborative filtering (CF) recommendation, but the contextual parameters in current approaches have same weights for all users. In this paper we propose an approach to learn the weights of contextual parameters for every user based on back-propagation (BP) neural network (NN). Then we present how to predict ratings based on well-known Slope One CF to achieve personalized context-aware (PC-aware) recommendation. Finally, we experimentally evaluate our approach and compare it to Slope One and context-aware CF. The experiment shows that our approach provide better recommendation results than them.


Recommendation Context Neural Network Collaborative Filtering Personalization 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Eirinaki, M., Vazirgiannis, M.: Web mining for web personalization. ACM Transactions on Internet Technology 3, 1–27 (2003)CrossRefGoogle Scholar
  2. 2.
    Lemire, D., Maclachlan, A.: Slope One Predictors for Online Rating-Based Collaborative Filtering. Society for Industrial Mathematics (2005)Google Scholar
  3. 3.
    Sarwar, B., Karypis, G., Konstan, J., Reidl, J.: Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th international conference on World Wide Web, pp. 285–295 (2001)Google Scholar
  4. 4.
    Chedrawy, Z., Abidi, S.S.R.: Case based reasoning for information personalization: using a context-sensitive compositional case adaptation approach. In: IEEE International Conference on Engineering of Intelligent Systems, pp. 1–6 (2006)Google Scholar
  5. 5.
    Adomavicius, G., Sankaranarayanan, R., Sen, S., Tuzhilin, A.: Incorporating contextual information in recommender systems using a multidimensional approach. ACM Transactions on Information Systems (TOIS) 23, 103–145 (2005)CrossRefGoogle Scholar
  6. 6.
    Gao, M., Zhongfu, W.: Incorporating pragmatic information in personalized recommendation systems. In: The 11th International Conference on Informatics and Semiotics in Organisations, pp. 156–164 (2009)Google Scholar
  7. 7.
    Dey, A.K.: Understanding and using context. Personal and Ubiquitous Computing 5, 4–7 (2001)CrossRefGoogle Scholar
  8. 8.
    Dey, A.K., Abowd, G.D.: Towards a better understanding of context and context-Awareness. In: CHI 2000 Workshop on the What, Who, Where, When, and How of Context-Awareness (2000)Google Scholar
  9. 9.
    Adomavicius, G., Tuzhilin, A.: Multidimensional recommender systems: A data warehousing approach. In: Fiege, L., Mühl, G., Wilhelm, U.G. (eds.) WELCOM 2001. LNCS, vol. 2232, p. 180. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  10. 10.
    Ilunga, M., Stephenson, D.: Infilling streamflow data using feed-forward back-propagation (BP) artificial neural networks: Application of standard BP and pseudo Mac Laurin power series BP techniques. Water SA 31, 171–176 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Min Gao
    • 1
  • Zhongfu Wu
    • 1
  1. 1.College of Computer ScienceChongqing UniversityChongqingChina

Personalised recommendations