Skip to main content
SpringerLink
Log in

Sentiment Analysis Using Large Language Models: A Case Study of GPT-3.5

  • Conference paper
  • First Online:
Data Science and Emerging Technologies (DaSET 2023)

Part of the book series: Lecture Notes on Data Engineering and Communications Technologies ((LNDECT,volume 191))

Included in the following conference series:

  • 47 Accesses

Abstract

Sentiment analysis, which utilizes machine learning, natural language processing, and computational linguistics, has been developed to comprehend the emotions and viewpoints of individuals on social media platforms. This area of research has undergone extensive investigation, leading to the integration of diverse algorithms and techniques specifically tailored to this objective. A recent breakthrough in the field of general AI is exemplified by Large Language Models, which have surpassed numerous research domains as quintessential achievements. This study examines the performance of GPT-3.5 in sentiment analysis. We evaluate its performance on established benchmark datasets as well as a collection of reviews extracted from Google Maps. The findings indicate that the Large Language Models can outperform traditional methods in the literature, and they do not require pre-processing, unlike traditional methods.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bonta V et al (2019) A comprehensive study on lexicon based approaches for sentiment analysis. AJCST. 8(S2):1–6. https://doi.org/10.51983/ajcst-2019.8.S2.2037

  2. Feldman R (2013) Techniques and applications for sentiment analysis. Commun ACM 56(4):82–89. https://doi.org/10.1145/2436256.2436274

    Article  Google Scholar 

  3. Haque MdR et al (2019) Performance analysis of different neural networks for sentiment analysis on IMDb movie reviews. In: 2019 3rd international conference on electrical, computer and telecommunication engineering (ICECTE), pp. 161–164 IEEE, Rajshahi, Bangladesh. https://doi.org/10.1109/ICECTE48615.2019.9303573

  4. Karthika P et al (2019) Sentiment analysis of social media network using random forest algorithm. In: 2019 IEEE international conference on intelligent techniques in control, optimization and signal processing (INCOS). IEEE, Tamil Nadu, India, pp 1–5. https://doi.org/10.1109/INCOS45849.2019.8951367

  5. Lo LS (2023) The CLEAR path: a framework for enhancing information literacy through prompt engineering. J Acad Librarianship 49(4):102720. https://doi.org/10.1016/j.acalib.2023.102720

  6. Maas A et al (2011) Learning word vectors for sentiment analysis. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies, pp 142–150

    Google Scholar 

  7. Mirchandani S et al (2023) Large language models as general pattern machines. https://doi.org/10.48550/ARXIV.2307.04721

  8. Nadi F Malaysian universities google map review. https://github.com/pharhadnadi/MalaysianUniversitiesGoogleMapReview

  9. Nandwani P, Verma R (2021) A review on sentiment analysis and emotion detection from text. Soc Netw Anal Min 11(1):81. https://doi.org/10.1007/s13278-021-00776-6

  10. Serrano-Guerrero J et al (2015) Sentiment analysis: a review and comparative analysis of web services. Inf Sci 311:18–38

    Article  Google Scholar 

  11. Styawati S, Mustofa K (2019) A support vector machine-firefly algorithm for movie opinion data classification. Indonesian J Comput Cybern Syst 13(3):219. https://doi.org/10.22146/ijccs.41302

  12. Wongkar M, Angdresey A (2019) Sentiment analysis using naive bayes algorithm of the data crawler: twitter. In: 2019 fourth international conference on informatics and computing (ICIC). IEEE, Semarang, Indonesia, pp 1–5. https://doi.org/10.1109/ICIC47613.2019.8985884

  13. Yadav J (2023) Sentiment analysis on social media. Qeios. https://doi.org/10.32388/YF9X04

  14. Zhou C et al (2023) A comprehensive survey on pretrained foundation models: a history from BERT to ChatGPT. https://doi.org/10.48550/ARXIV.2302.09419

Download references

Author information

Authors and Affiliations

  1. School of Information Technology, UNITAR International University, 47301, Kelana Jaya, Malaysia

    Farhad Nadi, Farhad Nadi, Hadi Naghavipour, Tahir Mehmood, Alliesya Binti Azman, Jeetha A/P Nagantheran, Kezia Sim Kui Ting, Nor Muhammad Ilman Bin Nor Adnan, Roshene A/P Sivarajan & Suita A/P Veerah

  2. Department of Information Technology, Universitas Sumatera Utara, Medan, Indonesia

    Romi Fadillah Rahmat

Authors
  1. Farhad Nadi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hadi Naghavipour
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tahir Mehmood
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alliesya Binti Azman
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jeetha A/P Nagantheran
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kezia Sim Kui Ting
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Nor Muhammad Ilman Bin Nor Adnan
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Roshene A/P Sivarajan
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Suita A/P Veerah
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Romi Fadillah Rahmat
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Farhad Nadi .

Editor information

Editors and Affiliations

  1. UNITAR Graduate School, UNITAR International University, Petaling Jaya, Malaysia

    Yap Bee Wah

  2. Faculty of Engineering and Technology, Liverpool John Moores University, Liverpool, UK

    Dhiya Al-Jumeily OBE

  3. University of Tennessee, Knoxville, TN, USA

    Michael W. Berry

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Nadi, F. et al. (2024). Sentiment Analysis Using Large Language Models: A Case Study of GPT-3.5. In: Bee Wah, Y., Al-Jumeily OBE, D., Berry, M.W. (eds) Data Science and Emerging Technologies. DaSET 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 191. Springer, Singapore. https://doi.org/10.1007/978-981-97-0293-0_12

Download citation

Publish with us

Policies and ethics

Search

Navigation