A Disentangled Adversarial Neural Topic Model for Separating Opinions from Plots in User Reviews

TL;DR

This paper introduces a neural topic model with adversarial training designed to separate subjective opinions from factual plot descriptions in reviews, improving interpretability and analysis of review content.

Contribution

It presents a novel disentangled neural topic model that effectively separates opinion and plot topics in reviews, with extensive experiments on a new dataset showing superior results.

Findings

Improved topic coherence and variety.

Consistent disentanglement of opinion and plot topics.

Enhanced sentiment classification performance.

Abstract

The flexibility of the inference process in Variational Autoencoders (VAEs) has recently led to revising traditional probabilistic topic models giving rise to Neural Topic Models (NTMs). Although these approaches have achieved significant results, surprisingly very little work has been done on how to disentangle the latent topics. Existing topic models when applied to reviews may extract topics associated with writers' subjective opinions mixed with those related to factual descriptions such as plot summaries in movie and book reviews. It is thus desirable to automatically separate opinion topics from plot/neutral ones enabling a better interpretability. In this paper, we propose a neural topic model combined with adversarial training to disentangle opinion topics from plot and neutral ones. We conduct an extensive experimental assessment introducing a new collection of movie and book reviews paired with their plots, namely MOBO dataset, showing an improved coherence and variety of topics, a consistent disentanglement rate, and sentiment classification performance superior to other supervised topic models.