Latent Multi-Criteria Ratings for Recommendations
This work addresses the need for more accurate recommendations in e-commerce or content platforms by enhancing multi-criteria models, though it appears incremental as it builds on existing methods with a novel data integration.
The paper tackled the problem of multi-criteria recommender systems by incorporating latent embeddings from user reviews to capture semantic relations, resulting in significant and consistent performance improvements across datasets and evaluation measures.
Multi-criteria recommender systems have been increasingly valuable for helping consumers identify the most relevant items based on different dimensions of user experiences. However, previously proposed multi-criteria models did not take into account latent embeddings generated from user reviews, which capture latent semantic relations between users and items. To address these concerns, we utilize variational autoencoders to map user reviews into latent embeddings, which are subsequently compressed into low-dimensional discrete vectors. The resulting compressed vectors constitute latent multi-criteria ratings that we use for the recommendation purposes via standard multi-criteria recommendation methods. We show that the proposed latent multi-criteria rating approach outperforms several baselines significantly and consistently across different datasets and performance evaluation measures.