Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
7-2024
Abstract
Sentiment analysis is the use of natural language processing to identify affective states and determine people’s opinions in various analytical applications such as customer reviews and social media analyses. Large language models (LLMs) such as GPT-4o demonstrate impressive performance in text generation tasks. Despite numerous studies in the extant literature, few have compared the performance of conventional machine learning models with LLMs for sentiment analysis. This study aims to fill this gap by conducting an evaluation of these models using a balanced dataset of 2,000 IMDb movie reviews. Our study shows that GPT-4o achieves the highest performance, while GPT-3.5 and FLAN-T5 models also show strong performance, being slightly below that of GPT-4o. Advanced LLMs outperform conventional machine learning models. Our findings highlight the advanced capabilities and user-friendliness of LLMs compared to conventional machine learning models. This research underscores the rapid evolution of LLMs for sentiment analysis.
Keywords
Sentiment Analysis, Large Language Models, GPT, FLAN-T5, Machine Learning, IMDb, Movie Reviews
Discipline
Databases and Information Systems | Graphics and Human Computer Interfaces
Research Areas
Data Science and Engineering
Publication
HCI International 2024: Late breaking papers, Washington, DC, June 29 - July 4
Volume
15382
First Page
291
Last Page
300
ISBN
9783031768279
Identifier
10.1007/978-3-031-76827-9_17
Publisher
Springer
City or Country
Cham
Citation
ZOU, Cui; CAI, Jingyuan; CHEN, Langtao; and NAH, Fiona Fui-hoon.
An exploratory study of conventional machine learning and large language models for sentiment analysis. (2024). HCI International 2024: Late breaking papers, Washington, DC, June 29 - July 4. 15382, 291-300.
Available at: https://ink.library.smu.edu.sg/sis_research/9961
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1007/978-3-031-76827-9_17
Included in
Databases and Information Systems Commons, Graphics and Human Computer Interfaces Commons
