M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysis

TL;DR

M-ABSA is a large-scale multilingual dataset for aspect-based sentiment analysis, enabling evaluation across 21 languages and 7 domains, and supporting diverse transfer learning and large language model research.

Contribution

The paper introduces M-ABSA, the most extensive multilingual ABSA dataset with automatic translation and human review, facilitating multilingual and multi-domain sentiment analysis research.

Findings

Dataset supports multilingual and multi-domain transfer learning

Enables evaluation of large language models on ABSA tasks

Highlights the importance of multilingual datasets for sentiment analysis

Abstract

Aspect-based sentiment analysis (ABSA) is a crucial task in information extraction and sentiment analysis, aiming to identify aspects with associated sentiment elements in text. However, existing ABSA datasets are predominantly English-centric, limiting the scope for multilingual evaluation and research. To bridge this gap, we present M-ABSA, a comprehensive dataset spanning 7 domains and 21 languages, making it the most extensive multilingual parallel dataset for ABSA to date. Our primary focus is on triplet extraction, which involves identifying aspect terms, aspect categories, and sentiment polarities. The dataset is constructed through an automatic translation process with human review to ensure quality. We perform extensive experiments using various baselines to assess performance and compatibility on M-ABSA. Our empirical findings highlight that the dataset enables diverse evaluation tasks, such as multilingual and multi-domain transfer learning, and large language model evaluation, underscoring its inclusivity and its potential to drive advancements in multilingual ABSA research.