Optimization of Recommendation System by Improving Serendipity and Grouping Users Based on Their Number of Data Points
DOI:
https://doi.org/10.52731/liir.v006.329Keywords:
Movie Recommendations, Recommendation Systems, Serendipity, User-based Collaborative FilteringAbstract
Information recommendation systems aim to deliver optimal content to users, but conventional methods often only suggest similar items, leading to user boredom and reduced recommendation effectiveness. This study addresses this limitation by focusing on “serendipity”, enhancing the unexpectedness of recommendations. We compared conventional methods, existing techniques, and six newly proposed approaches. Users were grouped into three categories based on the number of data points they evaluated to analyze the impact on recommendation performance. For users with fewer data points, the best approach was to recommend items significantly different from the average user preferences. For users with more data points, recommending items that other users disliked but held high value for the target user was most effective. These strategies improved diversity and unexpectedness without sacrificing usefulness, thereby successfully enhancing serendipity. This method shows promise in increasing user satisfaction by providing a more engaging recommendation experience.
References
D.T. Hawkins, L.R. Levy, and K.L. Montgomery, “Knowledge gateways: The building blocks,” Information Processing & Management, vol. 24, no. 4, 1988, pp. 459–468.
M.J. Bates, “The design of browsing and berrypicking techniques for the online search interface,” Online Review, vol. 13, no. 5, 1989, pp. 407–424.
D. Roy and M. Dutta, “A systematic review and research perspective on recommender systems,” Journal of Big Data, vol. 9, no. 59, 2022.
R. Mu, X. Zeng, and L. Han, “A survey of recommender systems based on deep learning,” IEEE Access, vol. 6, 2018, pp. 69009–69022.
K. Najmani, E.H. Benlahmar, N. Sael, and A. Zellou, “Collaborative filtering approach: A review of recent research,” in Advanced Intelligent Systems for Sustainable Development (AI2SD ’2020), Advances in Intelligent Systems and Computing, vol. 1418, Springer, Cham, 2022, pp. 151–163.
P. Lops, D. Jannach, C. Musto, T. Bogers, and M. Koolen, “Trends in content-based recommendation,” User Modeling and User-Adapted Interaction, vol. 29, no. 2, 2019, p. 239–249.
G. Figa` Talamanca and S. Arfini, “Through the newsfeed glass: Rethinking filter bubbles and echo chambers,” Philosophy & Technology, vol. 35, no. 20, 2022.
M.A. Qaz, M. Nadeem, S.S. Sohail, R. Imam, F. Doctor, Y. Himeur, A. Hussain, A. Amira, “Filter bubbles in recommender systems: Fact or fallacy―a systematic review,” WIREs Data Mining and Knowledge Discovery, vol. 13, no. 6, 2023.
S. Copeland, W. Ross, and M. Sand, “Introduction―a science of serendipity?,” in Serendipity Science: An Emerging Field and its Methods, Springer, Cham, 2023, pp. 1–16.
Y. Ping, Y. Li, and J. Zhu, “Beyond accuracy measures: The effect of diversity, novelty, and serendipity in recommender systems on user engagement,” Electronic Commerce Research, 2024.
S. Karimi, H.A. Rahmani, M. Naghiaei, and L. Safari, “Provider fairness and beyond- accuracy trade-offs in recommender systems,” in 6th FAccTRec Workshop: Responsible Recommendation, RecSys 2023, arXiv preprint arXiv:2309.04250, 2023.
H. Domoto, T. Uchiya, and I. Takumi, “Development of a hybrid information recommen-dation system considering serendipity,” in 2023 IEEE 12th Global Conference on Consumer Electronics (GCCE 2023), IEEE, Kyoto, 2023, pp. 1065–1066.
W. Ren, L. Wang, K. Liu, R. Guo, E.P. Lim, and Y. Fu, “Mitigating popularity bias in recommendation with unbalanced interactions: A gradient perspective,” in Proc. 22nd IEEE Int’l Conf. Data Mining (ICDM), IEEE, USA, 2022, pp. 1198–1203.
“Movielens dataset,” [Online]. Available: https://grouplens.org/datasets/movielens/. [Accessed: June 21, 2024].
A. Antiopi and B. Boutsinas, “Addressing the cold-start problem in recommender systems based on frequent patterns,” Algorithms, vol. 16, no. 4, 2023, p. 182. DOI: 10.3390/a16040182. License CC BY 4.0.
B. Lika, K. Kolomvatsos, and S. Hadjiefthymiades, “Facing the Cold Start Problem in Recommender Systems,” Expert Systems with Applications, vol. 41, no. 4, part 2, 2014, pp. 2065–2073.
I. Dokmanic´, R. Parhizkar, J. Ranieri, and M. Vetterli, “Euclidean distance matrices: Essential theory, algorithms, and applications,” IEEE Signal Processing Magazine, vol. 32, no. 6, 2015, pp. 12–30.
R.M. Roberts, Serendipity: Accidental discoveries in science, 2nd ed., John Wiley & Sons, New York, 1989.
R.J. Ziarani and R. Ravanmehr, “Serendipity in recommender systems: A systematic literature review,” Journal of Computer Science and Technology, vol. 36, no. 2, 2021.
T. Murakami, K. Mori, and R. Orihara, “Metrics for evaluating the serendipity of recommendation lists,” Lecture Notes in Computer Science (JSAI 2007), vol. 4914, Springer, 2008, pp. 40–46.
A. Bellog´ın, I. Cantador, and P. Castells, “A study of heterogeneity in recommendations for a social music service,” in Proc. 2010 Int’l Conf. Web Intelligence and Intelligent Agent Technology (WI-IAT), vol. 1, IEEE, Toronto, 2010, pp. 150–157.
X. Ning, C. Desrosiers and G. Karypis, “A Comprehensive Survey of Neighborhood-Based Recommendation Methods,” in Recommender Systems Handbook, vol. 2, Springer, 2015, pp. 37–76.
