Sentiment Analysis of Free Nutritious Meals Using Naive Bayes Algorithm

Authors

  • Beni Rahmatullah Universitas BSI
  • Suwanda Aditya Saputra Universitas BSI
  • Pungkas Budiono Universitas BSI
  • Dikdik Permana Wigandi Universitas BSI

DOI:

https://doi.org/10.46229/jifotech.v5i1.978

Keywords:

naive bayes, free, algorithm, preprocessing

Abstract

This study applies the Naive Bayes algorithm to analyze positive or negative comments regarding free nutritious meals on the YouTube platform of the Secretariat of State. Free nutritious meals often attract attention, but they also trigger a wide range of reactions, both positive and negative. In this context, the data is obtained using the Python programming language and automatically labeled using sentiment polarity. The Naive Bayes algorithm is used to classify comments as positive or negative based on the provided text. The model training process is conducted using a dataset containing 1,470 comments from YouTube accounts related to free nutritious meals, with 1,403 negative comments and 67 positive comments. After labeling the data, the next step is preprocessing, and the evaluation results show an accuracy of 87.35% for negative comments, a recall value of 56.76%, and an AUC value of 0.527. The classification performed indicates that the comments are mostly negative regarding free nutritious meals.

References

M. Choudhury and S. Islam, “Data Mining Techniques in Healthcare: A Review of Recent Developments and Applications,” J Med Syst, 2022.

S. Sharma and G. Kaur, “Analysis of social media data using Naive Bayes for sentiment analysis,” J Comput Sci, 2020.

R. Kaur and M. Kaur, “Sentiment analysis on product reviews using Naive Bayes and Support Vector Machine,” Journal of Artificial Intelligence and Data Mining, 2020.

W. Zhang and Z. Liu, “Sentiment analysis on social media data using Naive Bayes classification model,” Procedia Comput Sci, 2021.

L. Zhang and Z. Zhou, “Sentiment analysis of movie reviews using Naive Bayes classifier,” International Journal of Advanced Computer Science and Applications, 2020.

D. Pradhan and A. Das, “Review on sentiment analysis using Naive Bayes and deep learning techniques,” Proceedings of the International Conference on Artificial Intelligence and Data Analytics, 2023.

T. Ahmed, “Enhancing Naive Bayes Classifier for Big Data Applications,” pp. 52–67, 2023.

A. Patil and M. Joshi, “Analyzing sentiment of online customer reviews using Naive Bayes classifier,” International Journal of Research and Analytical Reviews, 2020.

P. Sunhare, R. R. Chowdhary, and M. K. Chattopadhyay, “Internet of things and data mining: An application oriented survey,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 6, pp. 3569–3590, Jun. 2022, doi: 10.1016/j.jksuci.2020.07.002.

D. Patel and S. Shah, “A Comprehensive Review on Sentiment Analysis Using Naive Bayes and Its Applications,” Journal of Information Technology and Applications, pp. 23–37, 2022.

V. K. Suda, Data Labeling in Machine Learning with Python: Explore modern ways to prepare labeled data for training and fine-tuning ML and generative AI models. Packt Publishing, 2024. [Online]. Available: http://ieeexplore.ieee.org/document/10769317

R. Kumar and S. Verma, “Opinion mining and sentiment analysis using Naive Bayes classifier,” Journal of Computer Science and Technolog, pp. 582–591, 2020.

Published

2025-03-28

How to Cite

Rahmatullah, B., Saputra, S. A. ., Budiono, P., & Wigandi, D. P. . (2025). Sentiment Analysis of Free Nutritious Meals Using Naive Bayes Algorithm. Journal of Information Technology, 5(1). https://doi.org/10.46229/jifotech.v5i1.978