Bridging the gap between ratings and true user opinions with dynamic review alignment for personalized recommendation.

Personalized recommender systems strive to deliver timely, accurate suggestions that reflect a user's current interests, yet they face challenges in aligning ratings with users' true thoughts and adapting to dynamic user behaviors under sparse user-item interactions. Ratings or implicit data often fail to reflect nuanced opinions, as users may assign high ratings despite expressing dissatisfaction in their reviews. Moreover, existing models struggle to adapt to temporal changes in user behaviors while handling the inherent noise and sparsity of real-world data. In this paper, we propose a dynamic multi-scale review alignment (DMRA) graph-based recommendation model to tackle these challenges. By incorporating multi-scale review extraction techniques, DMRA aligns textual insights with user-item interactions to uncover nuanced user opinions and mitigate rating biases. A sentiment-aware graph propagates semantic and sentiment information, while a memory-augmented module dynamically stores and updates user preferences in micro-cluster manner, balancing short-term and long-term interests. Furthermore, DMRA employs a contrastive learning mechanism to filter noise and inconsistencies in both ratings and reviews, ensuring robust recommendation. Extensive experiments on real-world datasets indicate that DMRA outperforms baselines, and has the capacity to promptly capture granular user preferences and item features and adapt to temporal dynamics, offering accurate and reliable personalized recommendations.