# Latent Multi-Criteria Ratings for Recommendations

## TL;DR

This paper introduces a novel approach that leverages variational autoencoders to generate latent multi-criteria ratings from user reviews, enhancing recommendation accuracy across various datasets.

## Contribution

It proposes a new method combining latent embeddings from reviews with multi-criteria recommendation techniques, improving performance over existing models.

## Key findings

- Outperforms baseline models significantly
- Consistent improvements across datasets
- Effective use of variational autoencoders for latent ratings

## Abstract

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.