GABSA-PT: Graph Neural Networks for Aspect-level Sentiment Analysis in Portuguese Language

Abstract

Aspect-based Sentiment Analysis is a Natural Language Processing task that aims to extract aspects from an opinionated text and identify the sentiment expressed by the opinion holder towards these aspects. Graph-based text representation has been shown to bring benefits to this task. While studies have demonstrated the effectiveness of this representation for ABSA using Graph Neural Networks in English, more work currently needs to be done evaluating this methodology for Portuguese language. In this article, we adapt a GNN known as DualGCN for sentiment classification using Brazilian Portuguese data. The model created using this approach achieved satisfactory results with a balanced accuracy of 75%.