The primary goal of this study is to gather insights about YouTube users’ opinions towards ChatGPT with the main features contributing to the users’ opinions. The second goal is to determine the overall distribution of positive and negative sentiments within YouTube comments related to ChatGPT. Using web scraping methodology on the YouTube platform, user comments were gathered, cleaned, and subjected to several data preprocessing steps. The model's performance was measured using a confusion matrix. Employing an 80:20 ratio for training and testing data, the Naive Bayes and SVM methods yielded respective accuracies of 72.5% and 75%. Visualization techniques were utilized to ascertain the topics covered by each sentiment expressed in user comments, alongside the features or keywords involved in user opinions. Through this analysis, it was revealed that user comments on YouTube exhibit more positive sentiments toward ChatGPT compared to negative sentiments.

Authors:
Evaristus Didik Madyatmadja, Bina Nusantara University, Indonesia
Debri Pristinella, Atmajaya Catholic University of Indonesia, Indonesia
Darren Angwyn, Bina Nusantara University, Indonesia
Ferris Leroy Winata, Bina Nusantara University, Indonesia
Tania Cresentia, Bina Nusantara University, Indonesia
Vivian Olivia Frederica Simanjuntak, Bina Nusantara University, indonesia

About the Presenter(s)
Prof. Evaristus Didik Madyatmadja currently is a full professor in School of Information Systems, Bina Nusantara (BINUS) University, Jakarta, Indonesia.

See this presentation on the full schedule – Tuesday Schedule

Bookmark

---

A Note to Presenters

To enhance academic profiles and showcase research, we encourage all presenters and co-presenters to include links to their public LinkedIn, ResearchGate profile, and research websites. Presenters may update their bio for their presentation by completing the form linked below by October 22, 2024.
- Presenter Information Update Form
Submitted changes will be reflected on November 01, 2024

Additionally, presenters should also update their IAFOR account details if there have been any changes to affiliations or biographies.
- https://submit.iafor.org/my-account/edit-account