A Joint Model for Aspect-Category Sentiment Analysis with Shared Sentiment Prediction Layer

TL;DR

This paper introduces a joint aspect-category sentiment analysis model with a shared sentiment prediction layer that transfers knowledge across categories, improving performance especially for data-scarce categories.

Contribution

The novel shared sentiment prediction layer enables effective knowledge transfer across aspect categories, addressing data deficiency issues in joint ACSA models.

Findings

Model outperforms existing joint models on SemEval-2016 datasets.

Shared layer improves sentiment prediction for low-data categories.

Effective transfer of sentiment knowledge across aspect categories.

Abstract

Aspect-category sentiment analysis (ACSA) aims to predict the aspect categories mentioned in texts and their corresponding sentiment polarities. Some joint models have been proposed to address this task. Given a text, these joint models detect all the aspect categories mentioned in the text and predict the sentiment polarities toward them at once. Although these joint models obtain promising performances, they train separate parameters for each aspect category and therefore suffer from data deficiency of some aspect categories. To solve this problem, we propose a novel joint model which contains a shared sentiment prediction layer. The shared sentiment prediction layer transfers sentiment knowledge between aspect categories and alleviates the problem caused by data deficiency. Experiments conducted on SemEval-2016 Datasets demonstrate the effectiveness of our model.