EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences

Cici Suhaeni, Hwan-Seung Yong

Applied Sciences · 29.08.2023 · 13 (17) · 9766

DOI: 10.3390/app13179766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 29.08.2023. Verfasst von Cici Suhaeni und 1 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea Agency for Infrastructure Technology Advancement (KAIA).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • Korea Agency for Infrastructure Technology Advancement (KAIA)

Zitieren

APA

Suhaeni, C., & Yong, H. (2023). Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences. Applied Sciences, 13(17), 9766. https://doi.org/10.3390/app13179766

Vancouver

Suhaeni C, Yong H. Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences. Applied Sciences. 2023;13(17):9766. doi:10.3390/app13179766

BibTeX
@article{Suhaeni2023,
  author = {Suhaeni, Cici and Yong, Hwan-Seung},
  title = {Mitigating Class Imbalance in Sentiment Analysis through GPT-3-Generated Synthetic Sentences},
  journal = {Applied Sciences},
  year = {2023},
  volume = {13},
  number = {17},
  pages = {9766},
  doi = {10.3390/app13179766}
}
Kostenlos starten →