International Journal of Computer Science & Network Security

International Journal of Computer Science & Network Security (국제컴퓨터통신보호논문지학회)
권호 표지
DOI QR코드

DOI QR Code

The Role of GPT Models in Sentiment Analysis Tasks

  • Mashael M. Alsulami (Department of Information Technology, College of Computers and Information Technology, Taif University)
  • Received : 2024.09.05
  • Published : 2024.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Sentiment analysis has become a pivotal component in understanding public opinion, market trends, and user experiences across various domains. The advent of GPT (Generative Pre-trained Transformer) models has revolutionized the landscape of natural language processing, introducing a new dimension to sentiment analysis. This comprehensive roadmap delves into the transformative impact of GPT models on sentiment analysis tasks, contrasting them with conventional methodologies. With an increasing need for nuanced and context-aware sentiment analysis, this study explores how GPT models, known for their ability to understand and generate human-like text, outperform traditional methods in capturing subtleties of sentiment expression. We scrutinize various case studies and benchmarks, highlighting GPT models' prowess in handling context, sarcasm, and idiomatic expressions. This roadmap not only underscores the superior performance of GPT models but also discusses challenges and future directions in this dynamic field, offering valuable insights for researchers, practitioners, and AI enthusiasts. The in-depth analysis provided in this paper serves as a testament to the transformational potential of GPT models in the realm of sentiment analysis.

Keywords

References

  1. J. L. Espejel, E. H. Ettifouri, M. S. Y. Alassan, E. M. Chouham, and W. Dahhane, "GPT-3.5, GPT-4, or BARD? Evaluating LLMs Reasoning Ability in Zero-Shot Setting and Performance Boosting Through Prompts," Nat. Lang. Process. J., vol. 5, no. 100032, May 2023.
  2. Z. Wang, Q. Xie, Z. Ding, Y. Feng, and R. Xia, "Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study," arXiv, Apr. 2023, [Online]. Available: http://arxiv.org/abs/2304.04339
  3. B. Liu, "Sentiment Lexicon Generation," in Sentiment Analysis and Opinion Mining, pp. 79-89, 2012, B. Liu, Ed. doi: 10.1007/978-3-031-02145-9_6.
  4. H. Hamdan, P. Bellot, and F. Bechet, "Sentiment Lexicon-Based Features for Sentiment Analysis in Short Text," Res. Comput. Sci., vol. 90, pp. 217-226, 2015. https://doi.org/10.13053/rcs-90-1-17
  5. U. Hassan, "Sentiment Analysis Using Machine Learning Classification Models," TechRxiv, May 2022. doi: 10.36227/techrxiv.19783384.v1.
  6. C. Wu, F. Wu, T. Qi, Y. Huang, and X. Xie, "Fastformer: Additive Attention Can Be All You Need," ArXiv, arXiv:2108.09084, Aug. 2021.
  7. T. de Kok, "Generative LLMs and Textual Analysis in Accounting: (Chat) GPT as Research Assistant?," SSRN Electron. J., 2023, doi: 10.2139/ssrn.4429658.
  8. P. Kumar and S. Kathuria, "Large Language Models (LLMs) for Natural Language Processing (NLP) of Oil and Gas Drilling Data," in SPE, Day 2 Tue, October 17, 2023. doi: 10.2118/215167-MS.
  9. E. Sezgin, J. Sirrianni, and S. L. Linwood, "Operationalizing and Implementing Pretrained, Large Artificial Intelligence Linguistic Models in the US Health Care System: Outlook of Generative Pretrained Transformer 3 (GPT-3) as a Service Model," JMIR Med. Inform., vol. 10, no. 2, p. e32875, Feb. 2022, doi: 10.2196/32875.
  10. K. Bhattarai, I. Y. Oh, J. M. Sierra, P. R. O. Payne, Z. B. Abrams, and A. M. Lai, "Leveraging GPT-4 for Identifying Clinical Phenotypes in Electronic Health Records: A Performance Comparison between GPT-4, GPT-3.5-turbo and spaCy's Rule-based & Machine Learning-based methods", bioRxiv, Apr. 2024. doi: 10.1101/2023.09.27.559788.
  11. T. Susnjak, "Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literature," arXiv, Feb. 2023, [Online]. http://arxiv.org/abs/2302.06474 https://doi.org/10.1007/978-1-0716-3561-2_14
  12. W. Zhang, Y. Deng, B. Liu, S. J. Pan, and L. Bing, "Sentiment Analysis in the Era of Large Language Models: A Reality Check," arXiv, May 2023, [Online]. Available: http://arxiv.org/abs/2305.15005
  13. L. Frohling and A. Zubiaga, "Feature-based detection of automated language models: tackling GPT-2, GPT-3 and Grover," PeerJ Comput. Sci., vol. 7, p. e443, Apr. 2021. doi: 10.7717/peerj-cs.443.
  14. J. Rudolph, S. Tan, and S. Tan, "ChatGPT: Bullshit Spewer or the End of Traditional Assessments in Higher Education?," J. Appl. Learn. Teach., vol. 6, no. 1, pp. 342-363, Jan. 2023. doi: 10.37074/jalt.2023.6.1.9.
  15. N. M. S. Surameery and M. Y. Shakor, "Use Chat GPT to Solve Programming Bugs," Int. J. Inf. Technol. Comput. Eng., no. 31, pp. 17-22, Jan. 2023. doi: 10.55529/ijitc.31.17.22.
  16. A. C. Gyllensten and M. Sahlgren, "Measuring Issue Ownership using Word Embeddings," in WASSA 2018 - 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop, Association for Computational Linguistics (ACL), 2018, pp. 149-155. doi: 10.18653/v1/P17.
  17. H. Wen and Z. Zhang, "SAKP: A Korean Sentiment Analysis Model via Knowledge Base and Prompt Tuning," in 2023 IEEE 3rd International Conference on Computer Communication and Artificial Intelligence (CCAI), IEEE, May 2023, pp. 147-152. doi: 10.1109/CCAI57533.2023.10201257.
  18. E. Azeraf, E. Monfrini, and W. Pieczynski, "Improving usual Naive Bayes classifier performances with Neural Naive Bayes based models," in International Conference on Pattern Recognition Applications and Methods, Nov. 2021.
  19. F. Sudirjo, K. Diantoro, J. A. Al-Gasawneh, H. Khootimah Azzaakiyyah, and A. M. Almaududi Ausat, "Application of ChatGPT in Improving Customer Sentiment Analysis for Businesses," Jurnal Teknologi Dan Sistem Informasi Bisnis, vol. 5, no. 3, pp. 283-288, Jul. 2023. doi: 10.47233/jteksis.v5i3.871.
  20. K. Yang, S. Ji, T. Zhang, Q. Xie, Z. Kuang, and S. Ananiadou, "Towards Interpretable Mental Health Analysis with Large Language Models," arXiv, Apr. 2023, [Online]. Available: http://arxiv.org/abs/2304.03347
  21. M. Leippold, "Swiss Finance Institute Research Paper Series N°23-11 Sentiment Spin: Attacking Financial Sentiment with GPT-3 Sentiment Spin: Attacking Financial Sentiment with GPT-3," Swiss Finance Institute Research Paper No. 23-11, Jan. 2023. [Online]. Available: https://ssrn.com/abstract=4337182
  22. C. Sarkar, B. Das, V.S. Rawat, J.B. Wahlang, A. Nongpiur, I. Tiewsoh, et al., "Artificial Intelligence and Machine Learning Technology Driven Modern Drug Discovery and Development," Int. J. Mol. Sci., vol. 24, no. 3, p. 2026, Jan. 2023, doi: 10.3390/ijms24032026.
  23. M. M. Fischer, "Neural Spatial Interaction Models: Network Training, Model Complexity and Generalization Performance," In Computational Science and Its Applications-ICCSA 2013: 13th International Conference, Ho Chi Minh City, Vietnam, June 24-27, 2013, Proceedings, Part IV 13 (pp. 1-16). Springer Berlin Heidelberg.
  24. A. Ioste, "Transforming the Output of Generative Pre-trained Transformer: The Influence of the PGI Framework on Attention Dynamics," arXiv, Aug. 2023, [Online]. Available: http://arxiv.org/abs/2308.13317
  25. M. Alawida, S. Mejri, A. Mehmood, B. Chikhaoui, and O. Isaac Abiodun, "A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity," Information, vol. 14, no. 8, p. 462, Aug. 2023. doi: 10.3390/info14080462.
  26. O. A. Garcia Valencia, C. Thongprayoon, C. C. Jadlowiec, S. A. Mao, J. Miao, and W. Cheungpasitporn, "Enhancing Kidney Transplant Care through the Integration of Chatbot," Healthcare, vol. 11, no. 18, p. 2518, Sep. 2023. doi: 10.3390/healthcare11182518.
  27. H. N. Tran and E. Cambria, "Ensemble Application of ELM and GPU for Real-Time Multimodal Sentiment Analysis," Memet. Comput., vol. 10, no. 1, pp. 3-13, Mar. 2018. doi: 10.1007/s12293-017-0228-3.
  28. Q. Zhong, L. Ding, J. Liu, B. Du, and D. Tao, "Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT," arXiv, Feb. 2023, [Online]. Available: http://arxiv.org/abs/2302.10198
  29. A. Buscemi and D. Proverbio, "ChatGPT vs Gemini vs LLaMA on Multilingual Sentiment Analysis," arXiv, Jan. 2024, [Online]. Available: http://arxiv.org/abs/2402.01715
  30. V. Hudecek and O. Dusek, "Are Large Language Models All You Need for Task-Oriented Dialogue?" [Online]. Available: https://openai.com/blog/chatgpt
  31. J. Yang, H. Jin, R. Tang, X. Han, Q. Feng, H. Jiang, et al., "Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond," ACM Trans. Knowl. Discov. Data., vol. 18, no. 6, pp. 1-32, Jul. 2024. doi: 10.1145/3649506.
  32. E. Kasneci, K. Sessler, S. Kuchemann, M. Bannert, D. Dementieva, F. Fischer, et al., "ChatGPT for Good? On Opportunities and Challenges of Large Language Models for Education," Learn. Individ. Diff., vol. 103. Elsevier Ltd, Apr. 01, 2023. doi: 10.1016/j.lindif.2023.102274.
  33. K. Kheiri and H. Karimi, "SentimentGPT: Exploiting GPT for Advanced Sentiment Analysis and its Departure from Current Machine Learning," arXiv, Jul. 2023.
  34. R. Anderson, C. Scala, J. Samuel, V. Kumar, and P. Jain, "Are Emotions Conveyed Across Machine Translations? Establishing an Analytical Process for the Effectiveness of Multilingual Sentiment Analysis with Italian Text," J. Big Data Artif. Intell., vol. 2, no. 1, Aug. 2023. doi: 10.20944/preprints202308.1003.v1.
  35. S. Cummins, L. Burd, and A. Hatch, "Using Feedback Tags and Sentiment Analysis to Generate Sharable Learning Resources Investigating Automated Sentiment Analysis of Feedback Tags in a Programming Course," in 2010 10th IEEE International Conference on Advanced Learning Technologies, IEEE, pp. 653-657, Jul. 2010. doi: 10.1109/ICALT.2010.186.