From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models
This work addresses aspect extraction challenges in sentiment analysis for researchers, but it appears incremental as it builds on existing ABSA methods with LLMs.
The study tackled the performance of Large Language Models in Aspect-Based Sentiment Analysis, particularly for implicit aspect extraction in a new domain, using a synthetic sports feedback dataset to evaluate aspect-polarity pair extraction and propose a new metric, finding both potential and limitations without specifying concrete numbers.
This study examines the performance of Large Language Models (LLMs) in Aspect-Based Sentiment Analysis (ABSA), with a focus on implicit aspect extraction in a novel domain. Using a synthetic sports feedback dataset, we evaluate open-weight LLMs' ability to extract aspect-polarity pairs and propose a metric to facilitate the evaluation of aspect extraction with generative models. Our findings highlight both the potential and limitations of LLMs in the ABSA task.