Friends Recommendation on Social Networks using the Bayesian Personalized Ranking-Matrix Factorization

Muhammad Haidir Ali; Z. K. A. Baizal

doi:10.47065/josyc.v5i2.4804

Muhammad Haidir Ali Telkom University, Bandung, Indonesia
Z. K. A. Baizal * Telkom University, Bandung, Indonesia

(*) Corresponding Author

DOI: https://doi.org/10.47065/josyc.v5i2.4804

Keywords: Recommendation System; Social Network; Bayesian Personalized Ranking; Matrix Factorization; Alternating Least Squares

Abstract

In the digital landscape of social networking, the challenge of improving friend recommendation systems is pivotal for enhancing user interaction and fostering social connections. Addressing this challenge, the current study innovates by fusing Bayesian Personalized Ranking (BPR) with Matrix Factorization (MF), culminating in a novel BPR-MF model designed for the intricacies of social network relationships. The study harnesses a rich dataset from LastFM, comprising 27,806 interactions among 7,624 users, to analyze mutual follower patterns and augment the precision of friend recommendations. Through rigorous preprocessing and systematic evaluation of the BPR-MF model against different numbers of latent factors, the research uncovers that a configuration of 20 latent factors is most effective, achieving an RMSE of 0.156 and an AUC ROC of 0.800. This discovery addresses the critical problem of balancing computational complexity with prediction accuracy in recommendation models. It also demonstrates the necessity for a nuanced, data-driven approach to generate relevant social connections. The research sets a new direction for future studies aiming to capitalize on user interaction data to offer precise friend suggestions, all while upholding user privacy and avoiding reliance on personal data.

Downloads

Download data is not yet available.

References

L. A. Adamic and E. Adar, “Friends and neighbors on the Web,” Soc Networks, vol. 25, no. 3, pp. 211–230, Jul. 2003, doi: 10.1016/S0378-8733(03)00009-1.

M. S. Granovetter, “The Strength of Weak Ties,” American Journal of Sociology, vol. 78, no. 6, pp. 1360–1380, May 1973, doi: 10.1086/225469.

M. Ameri, E. Honka, and Y. Xie, “From Strangers to Friends: Tie Formations and Online Activities in an Evolving Social Network,” Journal of Marketing Research, vol. 60, no. 2, pp. 329–354, Apr. 2023, doi: 10.1177/00222437221107900.

L. Berkani, “A semantic and social‐based collaborative recommendation of friends in social networks,” Softw Pract Exp, vol. 50, no. 8, pp. 1498–1519, Aug. 2020, doi: 10.1002/spe.2828.

C. Xu, “A novel recommendation method based on social network using matrix factorization technique,” Inf Process Manag, vol. 54, no. 3, pp. 463–474, May 2018, doi: 10.1016/j.ipm.2018.02.005.

J. Chen, J. Fang, W. Liu, T. Tang, X. Chen, and C. Yang, “Efficient and Portable ALS Matrix Factorization for Recommender Systems,” in 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), IEEE, May 2017, pp. 409–418. doi: 10.1109/IPDPSW.2017.91.

Y.-C. Lee, T. Kim, J. Choi, X. He, and S.-W. Kim, “M-BPR: A novel approach to improving BPR for recommendation with multi-type pair-wise preferences,” Inf Sci (N Y), vol. 547, pp. 255–270, Feb. 2021, doi: 10.1016/j.ins.2020.08.027.

D. Ding, M. Zhang, S.-Y. Li, J. Tang, X. Chen, and Z.-H. Zhou, “BayDNN,” in Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, New York, NY, USA: ACM, Nov. 2017, pp. 1479–1488. doi: 10.1145/3132847.3132941.

Akhilesh Narapareddy, “Recommender System Using Bayesian Personalized Ranking,” towardsdatascience.com.

A. Ameri, A. Bose, and M. Soltanalian, “Comprehensive Personalized Ranking Using One-Bit Comparison Data,” in 2019 IEEE Data Science Workshop (DSW), IEEE, Jun. 2019, pp. 338–342. doi: 10.1109/DSW.2019.8755595.

Shah and Shalin, “A Survey of Latent Factor Models for Recommender Systems and Personalization,” Authorea Preprints, 2023.

X. He, Z. He, X. Du, and T.-S. Chua, “Adversarial Personalized Ranking for Recommendation,” in The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, New York, NY, USA: ACM, Jun. 2018, pp. 355–364. doi: 10.1145/3209978.3209981.

N. Taneja and H. K. Thakur, “Evaluating the Scalability of Matrix Factorization and Neighborhood Based Recommender Systems,” International Journal of Information Technology and Computer Science, vol. 15, no. 1, pp. 21–29, Feb. 2023, doi: 10.5815/ijitcs.2023.01.03.

UCI Machine Learning Repository, “LastFM Asia Social Network.” DOI, 2020. doi: https://doi.org/10.24432/C5S904.

H. Zhang, I. Ganchev, N. S. Nikolov, Z. Ji, and M. O’Droma, “Weighted matrix factorization with Bayesian personalized ranking,” in 2017 Computing Conference, IEEE, Jul. 2017, pp. 307–311. doi: 10.1109/SAI.2017.8252119.

Dilip Yadav, Tushar Vaghasiya, Savita Ravate, and Prof. Vinit Raut, “Sparsity and Matrix Factorization in Recommender System,” IJARCCE, vol. 10, no. 4, Apr. 2021.

M. Nitti, L. Atzori, and I. P. Cvijikj, “Friendship Selection in the Social Internet of Things: Challenges and Possible Strategies,” IEEE Internet Things J, vol. 2, no. 3, pp. 240–247, Jun. 2015, doi: 10.1109/JIOT.2014.2384734.

A. Al-Nafjan, N. Alrashoudi, and H. Alrasheed, “Recommendation System Algorithms on Location-Based Social Networks: Comparative Study,” Information, vol. 13, no. 4, p. 188, Apr. 2022, doi: 10.3390/info13040188.

B. G. Galuzzi, I. Giordani, A. Candelieri, R. Perego, and F. Archetti, “Hyperparameter optimization for recommender systems through Bayesian optimization,” Computational Management Science, vol. 17, no. 4, pp. 495–515, Dec. 2020, doi: 10.1007/s10287-020-00376-3.

H. Ko, S. Lee, Y. Park, and A. Choi, “A Survey of Recommendation Systems: Recommendation Models, Techniques, and Application Fields,” Electronics (Basel), vol. 11, no. 1, p. 141, Jan. 2022, doi: 10.3390/electronics11010141.

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Friends Recommendation on Social Networks using the Bayesian Personalized Ranking-Matrix Factorization