Research on Hybrid Recommendation Algorithms for Film and Television Content Based on Big Data
Journal of Cases on Information Technology · 22.10.2026 · 28 (1) · 1-17
DOI: 10.4018/jcit.425683 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Cases on Information Technology, erschienen am 22.10.2026. Verfasst von Xiaolan Jia. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 3.0).
Abstract (Originalsprache)
Users often face information overload in the face of the rapid growth of streaming content. The author proposes a three-tiered hybrid recommendation algorithm for film and television content that integrates big data and recommendation concepts. The algorithm combines collaborative filtering with multimodal deep representation using an attention mechanism and incorporates real-time re-ranking to balance accuracy and diversity. Experimental results showed that the algorithm improves recommendation relevance, adapts to interest drift, and handles cold starts. Attention weights provide explanations, thereby enhancing system maintainability. The algorithm also features efficient calibration, preventing model aging. This approach drives innovation in scalable, explainable recommendation systems for large-scale platforms.
Zitieren
APA
Jia, X. (2026). Research on Hybrid Recommendation Algorithms for Film and Television Content Based on Big Data. Journal of Cases on Information Technology, 28(1), 1-17. https://doi.org/10.4018/jcit.425683
Vancouver
Jia X. Research on Hybrid Recommendation Algorithms for Film and Television Content Based on Big Data. Journal of Cases on Information Technology. 2026;28(1):1-17. doi:10.4018/jcit.425683
BibTeX
@article{Jia2026,
author = {Jia, Xiaolan},
title = {Research on Hybrid Recommendation Algorithms for Film and Television Content Based on Big Data},
journal = {Journal of Cases on Information Technology},
year = {2026},
volume = {28},
number = {1},
pages = {1--17},
doi = {10.4018/jcit.425683}
}
EUVIMED