DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis

2026-01-30

AI Summary

This work addresses the limitation of traditional aspect-based sentiment analysis (ABSA), which relies on coarse-grained polarity labels and fails to capture fine-grained emotional nuances. For the first time, dimensional sentiment modeling is introduced into ABSA through the construction of the first multilingual, multidomain dataset spanning six languages and four domains, comprising 76,958 aspect instances annotated with continuous valence–arousal (VA) scores. The study defines three novel subtasks and proposes a continuous F1 (cF1) metric to enable unified evaluation of both classification and regression approaches. By integrating large language model prompting, fine-tuning, and human validation, the project establishes a challenging benchmark for multilingual dimensional ABSA, offering a new paradigm and high-quality resources for fine-grained sentiment analysis.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Application Domains: Humanities & Computational Social Science
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Aspect-Based Sentiment Analysis (ABSA) focuses on extracting sentiment at a fine-grained aspect level and has been widely applied across real-world domains. However, existing ABSA research relies on coarse-grained categorical labels (e.g., positive, negative), which limits its ability to capture nuanced affective states. To address this limitation, we adopt a dimensional approach that represents sentiment with continuous valence-arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. To this end, we introduce DimABSA, the first multilingual, dimensional ABSA resource annotated with both traditional ABSA elements (aspect terms, aspect categories, and opinion terms) and newly introduced VA scores. This resource contains 76,958 aspect instances across 42,590 sentences, spanning six languages and four domains. We further introduce three subtasks that combine VA scores with different ABSA elements, providing a bridge from traditional ABSA to dimensional ABSA. Given that these subtasks involve both categorical and continuous outputs, we propose a new unified metric, continuous F1 (cF1), which incorporates VA prediction error into standard F1. We provide a comprehensive benchmark using both prompted and fine-tuned large language models across all subtasks. Our results show that DimABSA is a challenging benchmark and provides a foundation for advancing multilingual dimensional ABSA.

Problem

• Aspect-Based Sentiment Analysis
• Dimensional Sentiment
• Multilingual
• Multidomain
• Valence-Arousal

Innovation

• Dimensional ABSA
• Valence-Arousal
• Multilingual Dataset
• Continuous F1
• Aspect-Based Sentiment Analysis