AspeRa: Aspect-based Rating Prediction Model

TL;DR

AspeRa is an end-to-end aspect-based rating prediction model that leverages review texts to estimate user ratings and discover review aspects, improving prediction accuracy and interpretability.

Contribution

It introduces a novel joint embedding model with a dual-headed architecture and max-margin loss, outperforming existing models on real-world review datasets.

Findings

Outperforms state-of-the-art models like DeepCoNN, HFT, NARRE, and TransRev.

Effectively discovers review aspects that aid in explanation and user profiling.

Demonstrates the utility of aspect embeddings in recommender systems.

Abstract

We propose a novel end-to-end Aspect-based Rating Prediction model (AspeRa) that estimates user rating based on review texts for the items and at the same time discovers coherent aspects of reviews that can be used to explain predictions or profile users. The AspeRa model uses max-margin losses for joint item and user embedding learning and a dual-headed architecture; it significantly outperforms recently proposed state-of-the-art models such as DeepCoNN, HFT, NARRE, and TransRev on two real world data sets of user reviews. With qualitative examination of the aspects and quantitative evaluation of rating prediction models based on these aspects, we show how aspect embeddings can be used in a recommender system.