Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 용환승 | * |
dc.date.accessioned | 2024-02-15T05:11:42Z | - |
dc.date.available | 2024-02-15T05:11:42Z | - |
dc.date.issued | 2023 | * |
dc.identifier.issn | 2076-3417 | * |
dc.identifier.other | OAK-34007 | * |
dc.identifier.uri | https://dspace.ewha.ac.kr/handle/2015.oak/267740 | - |
dc.description.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. | * |
dc.language | English | * |
dc.publisher | Multidisciplinary Digital Publishing Institute (MDPI) | * |
dc.subject | GPT-3 | * |
dc.subject | imbalanced sentiment analysis | * |
dc.subject | sentiment analysis | * |
dc.subject | sentiment classification | * |
dc.subject | synthetics review generation | * |
dc.subject | text classification | * |
dc.subject | text generation | * |
dc.title | Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences | * |
dc.type | Article | * |
dc.relation.issue | 17 | * |
dc.relation.volume | 13 | * |
dc.relation.index | SCIE | * |
dc.relation.index | SCOPUS | * |
dc.relation.journaltitle | Applied Sciences (Switzerland) | * |
dc.identifier.doi | 10.3390/app13179766 | * |
dc.identifier.wosid | WOS:001062869400001 | * |
dc.identifier.scopusid | 2-s2.0-85170391826 | * |
dc.author.google | Suhaeni C. | * |
dc.author.google | Yong H.-S. | * |
dc.contributor.scopusid | 용환승(7101899751) | * |
dc.date.modifydate | 20240322133226 | * |