Web-based Sentiment Classifier for YouTube Comments

International Journal of Emerging Research in Science, Engineering, and Management

Vol. 2, Issue 2, pp. 01–06, February 2026

https://doi.org/10.58482/ijersem.v2i2.1

This work is licensed under a Creative Commons Attribution 4.0 International License .

Web-based Sentiment Classifier for YouTube Comments

Guggila Yasaswini, Abburi Thriveni, Karamala Praveena, Satyam Kumar Sharma, Valkuru Suman, D. Sudhakara

Department of CSE, Siddartha Institute of Science and Technology, Puttur, India.

Abstract

The current paper presents a web-based program that will evaluate the comments posted on YouTube on the basis of an analysis procedure that utilizes sentiment classification methods supported by contextual information gained through video transcripts. The system will first of all extract the comment, then, semantic search is performed to retrieve the most relevant transcript parts, and then the particular aspect is identified to which the user is agreeing, disagreeing, or assuming a neutral situation. A retrieval-augmented plan is implemented together with a language model, which adds the sentiment predictions with a human-readable explanation. This will increase the credibility of interpreting sophisticated remarks, especially those that may mention a particular spoken material in the video. The system aims at backing content creators, moderators, and viewers by providing a more subtle and dependable sentiment analysis.

Keywords: Sentiment Analysis, Natural Language Processing, YouTube Data API, Retrieval Augmented Generation, Naive Bayes.

📄 Download Full Text PDF

DOI: https://doi.org/10.58482/ijersem.v2i2.1

Open Access • Peer Reviewed Article

References

  1. F. Lovera and Y. Cardinale, “An Analytics Approach to Extracting Location and Sentiment Insights from Classified Social Media Data,” Decision Analytics Journal, vol. 16, p. 100624, Aug. 2025. https://doi.org/10.1016/j.dajour.2025.100624
  2. N. Shivsharan, V. Kambli, S. Dabholkar, A. Dalvi, and T. Sukali, “Evaluating Machine Learning Models for Sentiment Analysis of YouTube Comments and Creating an Accessible Web Application for Comment Analysis,” Procedia Computer Science, vol. 258, pp. 3165–3174, Jan. 2025. https://doi.org/10.1016/j.procs.2025.04.574
  3. P. Giganti, G. Errichiello, and P. M. Falcone, “Exploring Public Discourse on Green Hydrogen via YouTube Comments: A Comparative Sentiment Analysis Using VADER and ChatGPT,” Economic Analysis and Policy, vol. 88, pp. 2012–2030, Nov. 2025. https://doi.org/10.1016/j.eap.2025.11.014
  4. J. Ma, N. Sakib, F. I. Anik, and S. I. Ahamed, “Time-Synchronized Sentiment Labeling via Autonomous Online Comments Data Mining: A Multimodal Information Fusion on Large-Scale Multimedia Data,” Big Data Research, vol. 41, p. 100552, Jun. 2025. https://doi.org/10.1016/j.bdr.2025.100552
  5. Md. S. Islam, M. Ferdusi, and T. T. Aurpa, “Words of War: A Hybrid BERT-CNN Approach for Topic-Wise Sentiment Analysis on The Russia-Ukraine War,” Expert Systems With Applications, vol. 284, p. 127759, Apr. 2025. https://doi.org/10.1016/j.eswa.2025.127759
  6. E. Supriyadi and P. N. Makatita, “Sentiment Analysis of TikTok User Comments on QRIS Adoption in Indonesia Using IndoBERT,” Procedia Computer Science, vol. 269, pp. 121–130, Jan. 2025. https://doi.org/10.1016/j.procs.2025.08.265
  7. L. M. Gandy, L. V. Ivanitskaya, L. L. Bacon, and R. Bizri-Baryak, “Public Health Discussions on Social Media: Evaluating Automated Sentiment Analysis Methods,” JMIR Formative Research, vol. 9, p. e57395, Sep. 2024. https://doi.org/10.2196/57395
  8. P. Gamette and S. A. Asongu, “From Screens to Grids: A Web Scrapping Analysis of Electricity Access in Sub-Saharan Africa,” The Electricity Journal, vol. 38, no. 2, p. 107472, May 2025. https://doi.org/10.1016/j.tej.2025.107472
  9. J. Oh and J. Kim, “YouTube as a Social Listening Tool: Mining Housing Discourse on YouTube,” Cities, vol. 166, p. 106279, Jul. 2025. https://doi.org/10.1016/j.cities.2025.106279
  10. S. In and S. Chanchamnan, “Comparison of VADER and TextBlob Labeling for Sentiment Analysis Using Machine Learning and Deep Learning Models: A Study on Generative AI User Experience,” Acta Psychologica, vol. 263, p. 106268, Jan. 2026. https://doi.org/10.1016/j.actpsy.2026.106268
  11. M. Asghari, J. Nielsen, M. Gentili, N. Koizumi, and A. Elmaghraby, “Classifying Comments on Social Media Related to Living Kidney Donation: Machine Learning Training and Validation Study,” JMIR Medical Informatics, vol. 10, no. 11, p. e37884, Sep. 2022. https://doi.org/10.2196/37884
  12. M. Ahmad, I. Batyrshin, and G. Sidorov, “Sentiment Analysis Using a Large Language Model–Based Approach to Detect Opioids Mixed with Other Substances via Social Media: Method Development and Validation,” JMIR Infodemiology, vol. 5, p. e70525, Jun. 2025. https://doi.org/10.2196/70525
Download PDF

This article is part of Volume 2, Issue 2 (February 2026)

2026-02-28