Semantic Scholar Open Access 2025

EDTE: Dynamic Topic–Sentiment Cross-Attentive Fusion for Movie Recommendation

Bo Ma LuYao Liu Civil Simon Lau Yuhao Liu XueY Cui +1 lainnya

Abstrak

This paper presents EDTE: Dynamic Topic-Sentiment Cross-Attentive Fusion for Movie Recommendation, an end-to-end framework that integrates contextual topic modeling (CTM) and hierarchical sentiment analysis, combined with cross-attention and temporal attention to capture preference drift. EDTE encodes reviews into contextual topics and multi-granularity sentiment, aligns the two via a Transformer-based cross-attentive module, and weights historical interactions with recency- and relevance-aware temporal attention. On the Douban dataset (280 K users, 12,147 movies, 1.85 M reviews), EDTE achieves precision 0.768, recall 0.751, F1 0.759, and diversity 0.642; compared with TextCNN, LSTM, BERT4Rec, and CF, it shows consistent gains. Ablation indicates the topic and sentiment components contribute 0.4% and 0.3%, respectively; cross-domain evaluations on books and music show modest drops ($3.4 \%, 4.9 \%$); inference remains under 100 ms with near-linear scaling. Overall, the evidence suggests EDTE is effective and practically deployable for large-scale sequential movie recommendation.

Penulis (6)

Bo Ma

LuYao Liu Civil

Simon Lau

Yuhao Liu

XueY Cui

Rosie Zhang

Format Sitasi

APA MLA BibTeX

Ma, B., Civil, L.L., Lau, S., Liu, Y., Cui, X., Zhang, R. (2025). EDTE: Dynamic Topic–Sentiment Cross-Attentive Fusion for Movie Recommendation. https://doi.org/10.1109/EIECS67708.2025.11283457

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →

Lihat di Sumber doi.org/10.1109/EIECS67708.2025.11283457

Informasi Jurnal

Tahun Terbit: 2025
Bahasa: en
Sumber Database: Semantic Scholar
DOI: 10.1109/EIECS67708.2025.11283457
Akses: Open Access ✓