Abstract
Similarity computation is the critical component of collaborative filtering recommendation. Traditional similarity measures are usually calculated on user-item rating matrix directly, and couldn’t well describe users’ internal similar relations and personalization of rating habits. This paper proposes a novel similarity framework based on latent factor model, named LFSF (Latent Factor-based Similarity Framework). Different from the traditional similarity calculation based on rating matrix, the LFSF uses latent factor vectors instead of rating vectors to compute similarity. Since the latent factors are learned from the user feedback by the LFMs, the proposed LFSF appropriately merges advantages of the LFM into the similarity calculation, which improves the predictive accuracy of similarity measures. We illustrate the proposed framework in detail and propose related application instance of LFSF in this paper. We find that latent factors indicate the user preferences and reflect the item attributes more specifically, and the value of latent factors are less affected by user rating habits and item popularity. Experiments based on the real datasets show that the proposed LFSF is more rational and effective than traditional rating-based similarity.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Candillier, L., Meyer, F., Fessant, F.: Designing specific weighted similarity measures to improve collaborative filtering systems. In: Proceedings of ICDM, Leipzig, Germany, pp. 242–255(2008)
Tan, Z., He, L., Li, H., Wang, X.: Rating personalization improves accuracy: a proportion-based baseline estimate model for collaborative recommendation. In: Proceedings of CollaborateCOM, Beijing, China, pp. 104–114 (2016)
Cao, G., Kuang, L.: Identifying core users based on trust relationships and interest similarity in recommender system. In: Proceeding of ICWS, San Francisco, CA, USA, pp. 284–291(2016)
Tan, Z., He, L.: An efficient similarity measure for user-based collaborative filtering recommender systems inspired by the physical resonance principle. IEEE Access 5(1), 27211–27228 (2017)
Li, W., Xu, H., Ji, M., Xu, Z., Fang, H.: A hierarchy weighting similarity measure to improve user-based collaborative filtering algorithm. In: Proceedings of ICCC, Chengdu, China, pp. 843–846 (2016)
Guo, G., Zhang, J., Yorke-Smith, N.: A novel bayesian similarity measure for recommender systems. In: Proceedings of IJCAI, Beijing China, pp. 2619–2625 (2013)
Guo, G., Zhang, J., Yorke-Smith, N.: A novel evidence-based Bayesian similarity measure for recommender systems. ACM Trans. Web 10(2), 1–30 (2016)
Ahn, H.J.: A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem. Inf. Sci. 178(1), 37–51 (2008)
Breese, J.S., Heckerman, D., Kadie, C.: Empirical analysis of predictive algorithms for collaborative filtering. In: Proceedings of UAI, Madison, Wisconsin, pp. 43–52 (1998)
Lathia, N., Hailes, S., Capra, L.: The effect of correlation coefficients on communities of recommenders. In: Proceedings of SAC, Fortaleza, Ceara, Brazil, pp. 2000–2005 (2008)
Schwarz, M., Lobur, M., Stekh, Y.: Analysis of the effectiveness of similarity measures for recommender systems. In: Proceedings of CADSM, Lviv, Ukraine, pp. 275 –277 (2017)
Sarwar, B., Karypis, G., Konstan, J., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: Proceedings of the 10th International Conference on World Wide Web, pp. 285–295. ACM (2001)
Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 426–434. ACM (2008)
Kumar, R., Verma, B.K., Rastogi, S.S.: Social popularity based SVD++ recommender system. International Journal of Computer Applications, 87(14) (2014)
Guo, G., Zhang, J., Yorke-Smith, N.: TrustSVD: collaborative filtering with both the explicit and implicit influence of user trust and of item ratings. In: Proceedings of AAAI, pp. 123–129. (2015)
Acknowledgement
This work is supported by the National Natural Science Foundation of China under Grants No. 61772125, No. 61702084, No.61702090 and No. 61402097; and the Fundamental Research Funds for the Central Universities under Grant No. N151708005.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
He, L., Tan, Z., Guo, G., Chang, Q., Wu, D. (2018). LFSF: Latent Factor-Based Similarity Framework and Its Application for Collaborative Recommendation. In: Hong, R., Cheng, WH., Yamasaki, T., Wang, M., Ngo, CW. (eds) Advances in Multimedia Information Processing – PCM 2018. PCM 2018. Lecture Notes in Computer Science(), vol 11164. Springer, Cham. https://doi.org/10.1007/978-3-030-00776-8_68
Download citation
DOI: https://doi.org/10.1007/978-3-030-00776-8_68
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00775-1
Online ISBN: 978-3-030-00776-8
eBook Packages: Computer ScienceComputer Science (R0)