A Retail-Corpus for Aspect-Based Sentiment Analysis with Large Language Models

Oleg Silcenco, Marcos R. Machad, Wallace C. Ugulino, Daniel Braun
8/25/2025
cs.CL

No official code found. Best implementation: Responsible-NLP/ABSA-Retail-Corpus (1 star, last commit 2025-08-25).

Abstract

Aspect-based sentiment analysis enhances sentiment detection by associating it with specific aspects, offering deeper insights than traditional sentiment analysis. This study introduces a manually annotated dataset of 10,814 multilingual customer reviews covering brick-and-mortar retail stores, labeled with eight aspect categories and their sentiment. Using this dataset, the performance of GPT-4 and LLaMA-3 in aspect based sentiment analysis is evaluated to establish a baseline for the newly introduced data. The results show both models achieving over 85% accuracy, while GPT-4 outperforms LLaMA-3 overall with regard to all relevant metrics.

View on arXivView PDF

Code Implementations(1)

Responsible-NLP/ABSA-Retail-CorpusCommunity55%

Code and data for the paper "A Retail-Corpus for Aspect-Based Sentiment Analysis with Large Language Models"

10Python, Jupyter NotebookAug 5, 20251 years ago

Similar Papers

Learning to Extract Cross-Domain Aspects and Understanding Sentiments Using Large Language Models

86% match2025

Aspect Extraction from E-Commerce Product and Service Reviews

86% match2026

Multi-domain Multilingual Sentiment Analysis in Industry: Predicting Aspect-based Opinion Quadruples

85% match2025

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

84% match2024

Beyond the Star Rating: A Scalable Framework for Aspect-Based Sentiment Analysis Using LLMs and Text Classification

84% match2026

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

84% match2025

Cite this paper

@article{silcenco2025retailcorpus,
  title  = {A Retail-Corpus for Aspect-Based Sentiment Analysis with Large Language Models},
  author = {Oleg Silcenco and Marcos R. Machad and Wallace C. Ugulino and Daniel Braun},
  year   = {2025},
  eprint = {2508.17994},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.17994v1}
}

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/2508.17994.svg)](https://codeofpaper.com/paper/2508.17994)

Discussion