A Collaborative Filtering Algorithm for Hierarchical Filtering of Neighbors Based on Users’ Interest

  • Shuwei LeiEmail author
  • Jiang Wu
  • Jin Liu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)


In order to alleviate the sparsity of rating data and single rating similarity, from the perspective of optimizing similarity, this paper proposes a collaborative filtering algorithm for filtering neighbors hierarchically based on user interest (HFNCF). Firstly, this paper adopts the user’s rating number and rating size of each category to calculate user interest, and then improved similarity calculation, and join the interest coincidence degree factor to find similar users with the same interest of the target user, then find similar users with the target user having the largest interest cross-domain, and obtain the neighbor candidate set. Secondly, this paper considers the relative time changes between user ratings and adding time factors to improve the similarity of ratings to select the final similar neighbors. Finally, the comprehensive similarity is obtained by combining the two similarities, so that the target user’s ratings are predicted based on the rating of the final similar neighbors, and generate recommendations by the rating. Experimental proof, the algorithm proposed in this research achieves a lower MAE on MovieLens dataset compared to the traditional algorithm. Therefore, the HFNCF algorithm effectively selects neighbors, and improves the recommendation quality and accuracy.


HFNCF User interest User interest coincidence degree Time factor 


  1. 1.
    Adomavicius, G., Sankaranarayanan, R., Sen, S., Tuzhilin, A.: Incorporating contextual information in recommender systems using a multidimensional approach. ACM Trans. Inf. Syst. 23(1), 103–145 (2005)CrossRefGoogle Scholar
  2. 2.
    Adomavicius, G., Tuzhilin, A.: Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions. IEEE Trans. Knowl. Data Eng. 17(6), 734–749 (2005)CrossRefGoogle Scholar
  3. 3.
    Yao, P.P., Zou, D.S., Niu, B.J.: Collaborative filtering recommendation algorithm based on user preferences and project properties. Comput. Syst. Appl. (2015)Google Scholar
  4. 4.
    Liu, J., Wang, J.: An approach for recommending services based on user profile and interest similarity. In: IEEE International Conference on Software Engineering and Service Science, pp. 983–986. IEEE (2014)Google Scholar
  5. 5.
    Ye, F., Zhang, H.: A collaborative filtering recommendation based on users’ interest and correlation of items. In: International Conference on Audio, Language and Image Processing, pp. 515–520. IEEE (2017)Google Scholar
  6. 6.
    Koychev, I.: Gradual forgetting for adaptation to concept drift. In: Proceedings of ECAI 2000 Workshop Current Issues in Spatio-Temporal Reasoning, pp. 101–106 (2004)Google Scholar
  7. 7.
    Wu, W., Wang, J., Liu, R., Gu, Z., Liu, Y.: A user interest recommendation based on collaborative filtering. In: International Conference on Artificial Intelligence and Industrial Engineering (2016)Google Scholar
  8. 8.
    Gasmi, I., Seridi-Bouchelaghem, H., Hocine, L., Abdelkarim, B.: Collaborative filtering recommendation based on dynamic changes of user interest. Intell. Decis. Technol. 9(3), 271–281 (2015)CrossRefGoogle Scholar
  9. 9.
    Khurana, P., Parveen, S.: Approaches of recommender system: a survey. Int. J. Emerg. Trends Technol. Comput. Sci. 34(3), 134–138 (2016)CrossRefGoogle Scholar
  10. 10.
    Niwattanakul, S., Singthongchai, J., Naenudorn, E., Wanapu, S.: Using of Jaccard coefficient for keywords similarity. Lecture Notes in Engineering & Computer Science, vol. 2202, no. 1 (2013)Google Scholar
  11. 11.
    Kuzelewska, U.: Clustering algorithms in hybrid recommender system on movielens data. Stud. Logic Gramm. Rhetor. 37(1), 125–139 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.College of Information Science and TechnologyNorthwest UniversityXi’anChina

Personalised recommendations