IMPROVING LONG-TAIL RECOMMENDATION VIA ROULETTE WHEEL SELECTION USING HYBRID RATING AND TEMPORAL DECAY WEIGHTING
DOI:
https://doi.org/10.33480/jitk.v12i1.8240Keywords:
Hybrid Rating-Temporal Decay Weighting, Long-tail Recommendation, Popularity Bias, Sentence-BERT, Stochastic Roulette WheelAbstract
The phenomenon of information overload on digital platforms frequently leads to a skewed long-tail distribution, where user interactions concentrate on popular items while the majority remains undiscovered. This popularity bias is particularly acute in the book domain, where metaphorical titles defy traditional lexical matching, causing unique content to remain hidden in the long-tail area. While semantic models improve relevance, a significant research gap persists in mitigating the trade-off between accuracy and catalog exposure. This study proposes a novel stochastic framework by integrating Roulette Wheel Selection with hybrid rating and temporal decay weighting to enhance long-tail discoverability. To evaluate its generalizability, this mechanism was tested on the Goodreads Poetry dataset across four distinct content-based embedding models: SBERT-Tuned, SBERT, FastText, and Word2Vec. We conducted a rigorous comparative analysis between the proposed Stochastic (S) approach and Deterministic (D) Top-N selection. Experimental results demonstrate that the stochastic mechanism consistently improves catalog diversity across all baselines. SBERT-Tuned emerged as the most promising model, achieving a 461.71% increase in Catalog Coverage with a marginal 2.15% Recall reduction. Other models also exhibited significant gains, where the integration of Roulette Wheel Selection boosted coverage by 381.72% for FastText and 225.15% for Word2Vec, highlighting the framework's robustness. Furthermore, a consistent decrease in the Gini-index and an improvement in Novelty scores (ranging from +16% to +29%) confirm a more equitable distribution of item visibility. This research contributes a methodological advancement by proving that stochastic selection, guided by time-aware weighting, can effectively dismantle popularity bias without sacrificing relevance.
Downloads
References
[1] S. Saxena Deepak and Yasobant, “Information Overload,” in Encyclopedia of Big Data, C. L. Schintler Laurie A. and McNeely, Ed., Cham: Springer International Publishing, 2022, pp. 566–568. doi: 10.1007/978-3-319-32010-6_374.
[2] Y. Zoralioglu and E. Yalcin, “Dynamic feedback loops in recommender systems: Analyzing fairness, popularity bias, and user group disparities,” J. Intell. Inf. Syst., 2026, doi: 10.1007/s10844-026-01025-y.
[3] S. Z. U. Hassan, M. Rafi, and J. Frnda, “GCZRec: Generative Collaborative Zero-Shot Framework for Cold Start News Recommendation,” IEEE Access, vol. 12, pp. 16610–16620, 2024, doi: 10.1109/ACCESS.2024.3359053.
[4] F. Carnovalini, A. Rodà, and G. A. Wiggins, “Popularity Bias in Recommender Systems: The Search for Fairness in the Long Tail,” Information, vol. 16, no. 2, 2025, doi: 10.3390/info16020151.
[5] D. Zhang, S. Zheng, Y. Zhu, H. Yuan, J. Gong, and J. Tang, “MCAP: Low-Pass GNNs with Matrix Completion for Academic Recommendations,” ACM Trans. Inf. Syst., vol. 43, no. 2, Jan. 2025, doi: 10.1145/3698193.
[6] C. Wei, J. Liang, D. Liu, Z. Dai, M. Li, and F. Wang, “Meta Graph Learning for Long-tail Recommendation,” in Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, in KDD ’23. New York, NY, USA: Association for Computing Machinery, 2023, pp. 2512–2522. doi: 10.1145/3580305.3599428.
[7] K. Bauman, A. Vasilev, and A. Tuzhilin, “Does the Long Tail of Context Exist and Matter? The Case of Dialogue-based Recommender Systems,” in Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization, in UMAP ’24. New York, NY, USA: Association for Computing Machinery, 2024, pp. 273–278. doi: 10.1145/3627043.3659557.
[8] W. Shang and T. Underwood, “Disentangling semantic and prosodic features of English poetry,” Digital Scholarship in the Humanities, vol. 40, no. Supplement_1, pp. i87–i99, Jan. 2025, doi: 10.1093/llc/fqae008.
[9] X. Liu, G. Wang, and M. Z. A. Bhuiyan, “Personalised context-aware re-ranking in recommender system,” Conn. Sci., vol. 34, no. 1, pp. 319–338, Dec. 2022, doi: 10.1080/09540091.2021.1997915.
[10] X. Liu, G. Wang, and M. Zakirul Alam Bhuiyan, “Re‐ranking with multiple objective optimization in recommender system,” Transactions on Emerging Telecommunications Technologies, vol. 33, no. 1, Jan. 2022, doi: 10.1002/ett.4398.
[11] A. M. Yusuf, A. T. Wibowo, and K. R. Saleh, “Optimization of CTR Prediction in Recommendation with Rating-Time Decay,” in 2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT), 2023, pp. 232–238. doi: 10.1109/IAICT59002.2023.10205904.
[12] D. Lim and T. Lee, “Enhanced Recommender System with Sentiment Analysis of Review Text and SBERT Embeddings of Item Descriptions,” Mathematics, vol. 14, no. 1, 2026, doi: 10.3390/math14010184.
[13] M. Hanafi, M. A. Maulana, N. Fitria Kurniawa, A. B. Prasetyo, A. Dahlan, and M. A. Riyadhulhaq, “Effective Product Recommender System using Hybrid FastText, Attention and Probabilistic Matrix Factorization,” in 2024 16th International Conference on Information Technology and Electrical Engineering (ICITEE), 2024, pp. 7–12. doi: 10.1109/ICITEE62483.2024.10808774.
[14] R. Wang and Y. Shi, “Research on application of article recommendation algorithm based on Word2Vec and Tfidf,” in 2022 IEEE International Conference on Electrical Engineering, Big Data and Algorithms (EEBDA), 2022, pp. 454–457. doi: 10.1109/EEBDA53927.2022.9744824.
[15] A. Acharya, B. Singh, and N. Onoe, “LLM Based Generation of Item-Description for Recommendation System,” in Proceedings of the 17th ACM Conference on Recommender Systems, New York, NY, USA: ACM, Sep. 2023, pp. 1204–1207. doi: 10.1145/3604915.3610647.
[16] Q. Liu, N. Chen, T. Sakai, and X.-M. Wu, “ONCE: Boosting Content-based Recommendation with Both Open- and Closed-source Large Language Models,” in Proceedings of the 17th ACM International Conference on Web Search and Data Mining, New York, NY, USA: ACM, Mar. 2024, pp. 452–461. doi: 10.1145/3616855.3635845.
[17] W. Chen, Y. Zhao, L. Chen, and W. Pan, “Leave No One Behind: Fairness-Aware Cross-Domain Recommender Systems for Non-Overlapping Users,” in Proceedings of the Nineteenth ACM Conference on Recommender Systems, in RecSys ’25. New York, NY, USA: Association for Computing Machinery, 2025, pp. 226–236. doi: 10.1145/3705328.3748082.
[18] M. Singh, S. Indu, and N. Jayanthi, “Yoga Recommendation System: A GUI for Yoga Pose Detection and Health Benefit Mapping using allMiniLM-L6-v2 Embeddings,” in 2025 IEEE DELCON - International Conference on Recent Smart Technologies in Engineering for Sustainable Development, 2025, pp. 1–6. doi: 10.1109/DELCON68055.2025.11400399.
[19] Hartatik, L. Heryawan, and R. Pulungan, “Trust Decay-Based Temporal Learning for Dynamic Recommender Systems With Concept Drift Adaptation,” IEEE Access, vol. 13, pp. 110955–110971, 2025, doi: 10.1109/ACCESS.2025.3583186.
[20] J. Liu et al., “EVEDIT: Event-based Knowledge Editing for Deterministic Knowledge Propagation,” in Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, Y. Al-Onaizan, M. Bansal, and Y.-N. Chen, Eds., Miami, Florida, USA: Association for Computational Linguistics, Nov. 2024, pp. 4907–4926. doi: 10.18653/v1/2024.emnlp-main.282.
[21] A. Barolli, K. Bylykbashi, E. Qafzezi, S. Sakamoto, and L. Barolli, “Implementation of roulette wheel and random selection methods in a hybrid intelligent system: A comparison study for two Islands and Subway distributions considering different router replacement methods,” Appl. Soft Comput., vol. 131, p. 109805, 2022, doi: https://doi.org/10.1016/j.asoc.2022.109805.
[22] S. Vrijenhoek, S. Daniil, J. Sandel, and L. Hollink, “Diversity of What? On the Different Conceptualizations of Diversity in Recommender Systems,” in Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, in FAccT ’24. New York, NY, USA: Association for Computing Machinery, 2024, pp. 573–584. doi: 10.1145/3630106.3658926.
[23] N. and V. S. Castells Pablo and Hurley, “Novelty and Diversity in Recommender Systems,” in Recommender Systems Handbook, L. and S. B. Ricci Francesco and Rokach, Ed., New York, NY: Springer US, 2022, pp. 603–646. doi: 10.1007/978-1-0716-2197-4_16.
[24] A. El-Kishky et al., “TwHIN: Embedding the Twitter Heterogeneous Information Network for Personalized Recommendation,” in Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, New York, NY, USA: ACM, Aug. 2022, pp. 2842–2850. doi: 10.1145/3534678.3539080.
[25] K. Yan, “Optimizing an English text reading recommendation model by integrating collaborative filtering algorithm and FastText classification method,” Heliyon, vol. 10, no. 9, May 2024, doi: 10.1016/j.heliyon.2024.e30413.
[26] Y. Chu, H. Cao, Y. Diao, and H. Lin, “Refined SBERT: Representing sentence BERT in manifold space,” Neurocomputing, vol. 555, p. 126453, 2023, doi: https://doi.org/10.1016/j.neucom.2023.126453.
[27] K. Peng, M. Raghavan, E. Pierson, J. Kleinberg, and N. Garg, “Reconciling the Accuracy-Diversity Trade-off in Recommendations,” in Proceedings of the ACM Web Conference 2024, in WWW ’24. New York, NY, USA: Association for Computing Machinery, 2024, pp. 1318–1329. doi: 10.1145/3589334.3645625.
[28] M. C. Cakmak, N. Agarwal, and R. Oni, “The bias beneath: analyzing drift in YouTube’s algorithmic recommendations,” Soc. Netw. Anal. Min., vol. 14, no. 1, p. 171, 2024, doi: 10.1007/s13278-024-01343-5.
[29] J. Zhu, H. Wu, and A. Yaseen, “Sensitivity Analysis of a BERT-based scholarly recommendation system,” The International FLAIRS Conference Proceedings, vol. 35, May 2022, doi: 10.32473/flairs.v35i.130595.
[30] H.-S. Nguyen, Y. Liu, M. Mansoury, M. Aliannejadi, A. Hanjalic, and M. de Rijke, “A Reproducibility Study of Product-side Fairness in Bundle Recommendation,” in Proceedings of the Nineteenth ACM Conference on Recommender Systems, New York, NY, USA: ACM, Sep. 2025, pp. 696–705. doi: 10.1145/3705328.3748169.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Andy Maulana Yusuf, Miftah Farid Adiwisastra, Faizal Riza, Musrinah
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
