From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models

• DOI: 10.48550/arxiv.2503.20715
• Publication Date: 2025-03-26
• Authors: Nikita Neveditsin; Pawan Lingras; Vijay Mago
• Keywords: Data extraction; Sentiment Analysis

This study examines the performance of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA), with a focus on implicit aspect extraction novel domain. Using synthetic sports feedback dataset, we evaluate open-weight LLMs' ability to extract aspect-polarity pairs and propose metric facilitate evaluation generative models. Our findings highlight both potential limitations LLMs ABSA task.