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

Nikita Neveditsin, Pawan Lingras, Vijay Mago
3/26/2025
cs.CL

No confident code implementation found for this paper. 4 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 4 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

A Hybrid Approach To Aspect Based Sentiment Analysis Using Transfer Learning

89% match2024

Large Language Models Enhanced by Plug and Play Syntactic Knowledge for Aspect-based Sentiment Analysis

88% match2025

Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMs

87% match2026

LLaMA-Based Models for Aspect-Based Sentiment Analysis

87% match2025

LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data Augmentation

87% match2025

Exploring Large Language Models for Multimodal Sentiment Analysis: Challenges, Benchmarks, and Future Directions

87% match2024

Cite this paper

@article{neveditsin2025from,
  title  = {From Annotation to Adaptation: Metrics, Synthetic Data, and Aspect Extraction for Aspect-Based Sentiment Analysis with Large Language Models},
  author = {Nikita Neveditsin and Pawan Lingras and Vijay Mago},
  year   = {2025},
  eprint = {2503.20715},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2503.20715v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2503.20715.svg)](https://codeofpaper.com/paper/2503.20715)

Discussion