NL repository
menu
검색
Library
Browse
Communities & Collections
By Date
Authors
Titles
Subject
My Repository
My Account
Receive email updates
Edit Profile
DSpace at EWHA
인공지능대학
컴퓨터공학과
Journal papers
View : 165 Download: 0
Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences
Title
Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences
Authors
Suhaeni C.
;
Yong H.-S.
Ewha Authors
용환승
SCOPUS Author ID
용환승
Issue Date
2023
Journal Title
Applied Sciences (Switzerland)
ISSN
2076-3417
Citation
Applied Sciences (Switzerland) vol. 13, no. 17
Keywords
GPT-3
;
imbalanced sentiment analysis
;
sentiment analysis
;
sentiment classification
;
synthetics review generation
;
text classification
;
text generation
Publisher
Multidisciplinary Digital Publishing Institute (MDPI)
Indexed
SCIE; SCOPUS
Document Type
Article
Abstract
In this paper, we explore the effectiveness of the GPT-3 model in tackling imbalanced sentiment analysis, focusing on the Coursera online course review dataset that exhibits high imbalance. Training on such skewed datasets often results in a bias towards the majority class, undermining the classification performance for minority sentiments, thereby accentuating the necessity for a balanced dataset. Two primary initiatives were undertaken: (1) synthetic review generation via fine-tuning of the Davinci base model from GPT-3 and (2) sentiment classification utilizing nine models on both imbalanced and balanced datasets. The results indicate that good-quality synthetic reviews substantially enhance sentiment classification performance. Every model demonstrated an improvement in accuracy, with an average increase of approximately 12.76% on the balanced dataset. Among all the models, the Multinomial Naïve Bayes achieved the highest accuracy, registering 75.12% on the balanced dataset. This study underscores the potential of the GPT-3 model as a feasible solution for addressing data imbalance in sentiment analysis and offers significant insights for future research. © 2023 by the authors.
DOI
10.3390/app13179766
Appears in Collections:
인공지능대학
>
컴퓨터공학과
>
Journal papers
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML
Show full item record
Find@EWHA
트윗하기
BROWSE
Communities & Collections
By Date
Authors
Titles
Subject