DeepLTRS: A Deep Latent Recommender System based on User Ratings and Reviews

Dingge Liang (1) , Marco Corneli (1, 2, 3) , Charles Bouveyron (1, 3) , Pierre Latouche (4)

1 MAASAI - Modèles et algorithmes pour l’intelligence artificielle
2 MSI - Maison de la Modélisation, de la Simulation et des Interactions [Sophia-Antipolis]
3 LJAD - Laboratoire Jean Alexandre Dieudonné
4 MAP5 - UMR 8145 - Mathématiques Appliquées Paris 5

We introduce a deep latent recommender system named deepLTRS in order to provide users with high quality recommendations based on observed user ratings and texts of product reviews. The underlying motivation is that, when a user scores only a few products, the texts used in the reviews represent a significant source of information. Using this information can alleviate data sparsity, thereby enhancing the predictive ability of the model. Our approach adopts a variational auto-encoder (VAE) architecture as a generative deep latent variable model for both the ordinal matrix, encoding users scores about products, and the document-term matrix, encoding the reviews. Moreover, different from unique user-based or item-based models, deepLTRS assumes latent representations for both users and products. An alternated user/product mini-batching optimization structure is proposed to jointly capture user and product preferences. Numerical experiments on simulated and real-world data sets demonstrate that deepLTRS outperforms the state-of-the-art, in particular in context of extreme data sparsity.

Mots clés: Recommender system; Variational auto-encoder; Latent variable model; Matrix factorization; Topic modeling

Domaines: Intelligence artificielle [cs.AI]; Réseau de neurones [cs.NE]

Dingge Liang, Marco Corneli, Charles Bouveyron, Pierre Latouche. DeepLTRS: A Deep Latent Recommender System based on User Ratings and Reviews. Pattern Recognition Letters, 2021, ⟨10.1016/j.patrec.2021.10.022⟩. ⟨hal-03021362v1⟩