Abstract:
Many reviews-rating integration studies have improved recommendation performance. These works still have flaws: (1) Dynamically integrating review and interaction data features is often overlooked, but treating them equally may lead to a misunderstanding of user preferences. (2) Soft attention methods model word local semantic information.
The attention map is neither discriminatory nor detailed because features may contain irrelevant information. We propose AHAG, an adaptive hierarchical attention-enhanced gated network that integrates reviews for item recommendation.
AHAG adaptively incorporates reviews to reveal user intentions. We use a gated network to dynamically fuse extracted features and select user-preference-relevant features. A hierarchical attention mechanism learns important semantic information features and their dynamic interaction to distinguish fine-grained features.
To predict ratings, neural factorization machines use high-order non-linear interaction. The proposed AHAG significantly outperforms state-of-the-art methods on seven real-world datasets. To improve recommendation task interpretability, the attention mechanism can highlight relevant review information.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
