A Novel Neutrosophic Recommender System Model Using Entropy Theory and Collaborative Filtering Algorithm
International Journal of Intelligent Systems · 2026-01 · 2026 (1)
DOI: 10.1155/int/5244922 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Intelligent Systems, online erschienen am 28.06.2026. Verfasst von Nguyen-Giap Cu und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
User behavior data used in recommender systems are frequently inconsistent, uncertain, and hesitant, making it challenging to model using common traditional techniques. Fuzzy logic, known for its ability to handle uncertainty, has therefore been widely adopted. Among the variants and extensions of fuzzy logic, the neutrosophic set, characterized by three components—truth, indeterminacy, and falsity, offers a powerful and effective framework for representing and processing user behavior data in recommender systems. However, one major challenge in applying fuzzy theory to recommender systems lies in the fuzzification process, which directly influences model quality. In this study, a collaborative filtering‐based recommendation system model is developed using the neutrosophic set as a foundational framework. To improve the fuzzification stage, entropy theory is employed to optimize the fuzzification process. Furthermore, operations within the neutrosophic‐based recommendation system model are studied and optimized to better accommodate various application contexts. A ranking accuracy metric tailored for both neutrosophic data and crisp data is proposed, enabling precise evaluation and comparison of recommendation errors. Based on this metric, a hyperparameter learning method is introduced to efficiently search for optimal fuzzification parameters together with other model‐specific parameters, thereby enhancing overall recommendation performance. Experiments on a public dataset present remarkable performance and potential application of proposed entropy‐based neutrosophic recommender system framework.
Zitieren
APA
Cu, N., Nghiem, T., & Tran, L. (2026). A Novel Neutrosophic Recommender System Model Using Entropy Theory and Collaborative Filtering Algorithm. International Journal of Intelligent Systems, 2026(1). https://doi.org/10.1155/int/5244922
Vancouver
Cu N, Nghiem T, Tran L. A Novel Neutrosophic Recommender System Model Using Entropy Theory and Collaborative Filtering Algorithm. International Journal of Intelligent Systems. 2026;2026(1). doi:10.1155/int/5244922
BibTeX
@article{Cu2026,
author = {Cu, Nguyen-Giap and Nghiem, Thi-Lich and Tran, Le-Kim-Danh},
title = {A Novel Neutrosophic Recommender System Model Using Entropy Theory and Collaborative Filtering Algorithm},
journal = {International Journal of Intelligent Systems},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/int/5244922}
}
EUVIMED