ABSTRACT
Conventional recommender systems have a potential problem of hyper-personalization that produces biased recommendations, decreasing the diversity of items. Concerning this issue, serendipity-oriented recommender systems have been introduced as an alternative to increasing recommendation diversity. However, these systems have a drawback in potentially recommending uninteresting items from a target user's perspective. To overcome this limitation, the present study introduces a novel algorithm to recommend diverse items that are likely to be favored via fusing serendipity into existing algorithms with maintaining accuracy. Specifically, we incorporate elements of serendipity into session- and graph neural network-based recommender systems by utilizing not only unexpected but also relevant data from historical data. Furthermore, our algorithm reflects the personalized balancing for trade-off via a user-controllable parameter. In the application of our algorithm, the experimental results on two real-world datasets show the algorithm's trade-off between accuracy and diversity and its potential from the user-centric perspective. This study contributes to proposing a new algorithm that provides not solely useful but also varied recommendations to broaden users’ horizons and to simple and clear algorithmic improvement by its application.
Supplemental Material
- Afridi, A.H. 2018. User Control and Serendipitous Recommendations in Learning Environments. Procedia Computer Science. 130, (2018), 214–221. DOI:https://doi.org/10.1016/j.procs.2018.04.032.Google ScholarDigital Library
- Ge, M., Delgado-Battenfeld, C. and Jannach, D. 2010. Beyond accuracy. Proceedings of the fourth ACM conference on Recommender systems - RecSys ’10 (New York, New York, USA, 2010), 257.Google Scholar
- Karpus, A., Vagliano, I. and Goczyła, K. 2017. Serendipitous Recommendations Through Ontology-Based Contextual Pre-filtering. Stanisław Kozielski, Dariusz Mrozek, Paweł Kasprowski, Bożena Małysiak-Mrozek, and Daniel Kostrzewa, eds. 246–259.Google Scholar
- Khoshahval, S., Farnaghi, M., Taleai, M. and Mansourian, A. 2018. A Personalized Location-Based and Serendipity-Oriented Point of Interest Recommender Assistant Based on Behavioral Patterns. 271–289.Google Scholar
- Kito, N., Oku, K. and Kawagoe, K. 2014. Correlation analysis among the metadata-based similarity, acoustic-based distance, and serendipity of music. Proceedings of the 19th International Database Engineering & Applications Symposium on - IDEAS ’15 (New York, New York, USA, 2014), 198–199.Google ScholarDigital Library
- Kotkov, D., Veijalainen, J. and Wang, S. 2020. How does serendipity affect diversity in recommender systems? A serendipity-oriented greedy algorithm. Computing. 102, 2 (Feb. 2020), 393–411. DOI:https://doi.org/10.1007/s00607-018-0687-5.Google ScholarDigital Library
- Liu, Y., Xiao, Y., Wu, Q., Miao, C., Zhang, J., Zhao, B. and Tang, H. 2020. Diversified Interactive Recommendation with Implicit Feedback. Proceedings of the AAAI Conference on Artificial Intelligence. 34, 04 (Apr. 2020), 4932–4939. DOI:https://doi.org/10.1609/aaai.v34i04.5931.Google ScholarCross Ref
- McNee, S.M., Riedl, J. and Konstan, J.A. 2006. Being accurate is not enough. CHI ’06 Extended Abstracts on Human Factors in Computing Systems (New York, NY, USA, Apr. 2006), 1097–1101.Google Scholar
- Mitheran, S., Java, A., Sahu, S.K. and Shaikh, A. 2021. Introducing Self-Attention to Target Attentive Graph Neural Networks. (Jul. 2021).Google Scholar
- Wang, C.-D., Deng, Z.-H., Lai, J.-H. and Yu, P.S. 2019. Serendipitous Recommendation in E-Commerce Using Innovator-Based Collaborative Filtering. IEEE Transactions on Cybernetics. 49, 7 (Jul. 2019), 2678–2692. DOI:https://doi.org/10.1109/TCYB.2018.2841924.Google ScholarCross Ref
- Wang, S., Cao, L., Wang, Y., Sheng, Q.Z., Orgun, M.A. and Lian, D. 2022. A Survey on Session-based Recommender Systems. ACM Computing Surveys. 54, 7 (Sep. 2022), 1–38. DOI:https://doi.org/10.1145/3465401.Google ScholarDigital Library
- Wu, S., Sun, F., Zhang, W., Xie, X. and Cui, B. 2020. Graph Neural Networks in Recommender Systems: A Survey. (Nov. 2020).Google Scholar
- Wu, S., Tang, Y., Zhu, Y., Wang, L., Xie, X. and Tan, T. 2019. Session-Based Recommendation with Graph Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence. 33, (Jul. 2019), 346–353. DOI:https://doi.org/10.1609/aaai.v33i01.3301346.Google ScholarDigital Library
- Yu, F., Zhu, Y., Liu, Q., Wu, S., Wang, L. and Tan, T. 2020. TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (New York, NY, USA, Jul. 2020), 1921–1924.Google ScholarDigital Library
- Yu, H., Wang, Y., Fan, Y., Meng, S. and Huang, R. 2018. Accuracy Is Not Enough: Serendipity Should Be Considered More. 231–241.Google Scholar
- Ziarani, R.J. and Ravanmehr, R. 2021. Serendipity in Recommender Systems: A Systematic Literature Review. Journal of Computer Science and Technology. 36, 2 (Apr. 2021), 375–396. DOI:https://doi.org/10.1007/s11390-020-0135-9.Google ScholarDigital Library
Index Terms
- Serendipity into session-based recommendation: Focusing on unexpectedness, relevance, and usefulness of recommendations
Recommendations
Rethinking Serendipity in Recommender Systems
CHIIR '23: Proceedings of the 2023 Conference on Human Information Interaction and RetrievalRecommender systems suggest items, such as movies or books, to users based on their interests. These systems often suggest items that users are either already familiar with or could easily have found on their own without additional assistance. To ...
How Serendipity Improves User Satisfaction with Recommendations? A Large-Scale User Evaluation
WWW '19: The World Wide Web ConferenceRecommendation serendipity is being increasingly recognized as being equally important as the other beyond-accuracy objectives (such as novelty and diversity), in eliminating the “filter bubble” phenomenon of the traditional recommender systems. However,...
Investigating serendipity in recommender systems based on real user feedback
SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied ComputingOver the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-...
Comments