An adaptive deep learning method for item recommendation system
For many years user textual reviews have been exploited to model user/item representations for enhancing the performance of the Recommender System (RS). However, the traditional methods of the RSs basically rely on the static user/item feature vectors and ignore the fine-grained user–item interactio...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier B.V.
2021
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/96072/ http://dx.doi.org/10.1016/j.knosys.2020.106681 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Malaysia |
| Summary: | For many years user textual reviews have been exploited to model user/item representations for enhancing the performance of the Recommender System (RS). However, the traditional methods of the RSs basically rely on the static user/item feature vectors and ignore the fine-grained user–item interactions which could affect the accuracy of the RSs. Thus, this paper proposes a RS model that exploits neural attention techniques to learn adaptive user/item representations and fine-grained user–item interaction for enhancing the accuracy of the item recommendation. An attentive pooling layer is first designed based on the Convolutional Neural Network (CNN) to learn the adaptive latent features of the user/item from reviews. A mutual attention network technique is then introduced for modelling the fine-grained user–item? interaction to enable jointly capturing the most informative features at the higher granularity. Finally, a prediction layer is then applied for the final prediction based on the adaptive user/item representation and the user/item importance. We extensively conduct a series of experiments using Amazon and Yelp reviews, and the results demonstrate that our proposed model performs better than the existing methods in terms of both rating prediction and ranking performances. Statistical paired test show that all the performance improvements are significant at p<0.05. |
|---|