Sentiment Analysis of Nakba Oral Histories: A Critical Study of Large Language Models

Files

Sentiment.pdf (486.75 KB)

Links to Files

https://aclanthology.org/2025.nakbanlp-1.4/

Permanent Link

http://hdl.handle.net/11603/40462

Collections

UMBC Data Science
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0002-6835-8338

Date

2025-01

Type of Work

conference papers and proceedings
Text

Department

Program

Citation of Original Publication

Ashqar, Huthaifa I. “Sentiment Analysis of Nakba Oral Histories: A Critical Study of Large Language Models.” In Proceedings of the First International Workshop on Nakba Narratives as Language Resources, edited by Mustafa Jarrar, Habash Habash, and Mo El-Haj. Association for Computational Linguistics, 2025. https://aclanthology.org/2025.nakbanlp-1.4/.

Rights

Attribution 4.0 International

Subjects

Abstract

This study explores the use of Large Language Models (LLMs), specifically ChatGPT, for sentiment analysis of Nakba oral histories, which document the experiences of Palestinian refugees. The study compares sentiment analysis results from full testimonies (average 2500 words) and their summarized versions (300 words). The findings reveal that summarization increased positive sentiment and decreased negative sentiment, suggesting that the process may highlight more hopeful themes while oversimplifying emotional complexities. The study highlights both the potential and limitations of using LLMs for analyzing sensitive, trauma-based narratives and calls for further research to improve sentiment analysis in such contexts.