From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models
By: Nikita Neveditsin, Pawan Lingras, Vijay Mago
Potential Business Impact:
Helps computers understand feelings about sports.
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.
Similar Papers
LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation
Computation and Language
Lets computers understand feelings in any language.
Large Language Models for Czech Aspect-Based Sentiment Analysis
Computation and Language
Helps computers understand feelings about specific things.
LLaMA-Based Models for Aspect-Based Sentiment Analysis
Computation and Language
Makes computers understand feelings about many things.