SENTIMENT ANALYSIS ON ARTIFICIAL INTELLIGENCE TECHNOLOGY USING NAIVE BAYES CLASSIFIER
DOI:
https://doi.org/10.35450/jip.v12i03.637Keywords:
Artificial Intelligence, Naïve Bayes Classifier, Public Opinion, Sentiment Analysis, Text MiningAbstract
The advancement of Artificial Intelligence (AI) technology has significantly impacted various aspects of life. However, these technological developments often elicit diverse responses from the public, including enthusiasm and concern. This study aims to analyze public sentiment toward AI developments using the Naive Bayes Classifier algorithm. The research collected AI-related tweets through data crawling, preprocessing, sentiment labeling, and feature extraction using TF-IDF. To address the class imbalance in the data, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. The Naive Bayes Classifier model was then used to classify public sentiment into positive, negative, and neutral categories. Evaluation results indicate that the Naive Bayes Classifier achieved an overall accuracy of 70%, with a precision of 72%, recall of 70%, and F1-score of 71%. Although the model is relatively effective in identifying positive sentiments, challenges remain in distinguishing negative and neutral sentiments accurately. Factors affecting model performance, such as data preprocessing quality and limited dataset diversity, are discussed as areas for improvement in future research
Downloads
References
Aydogan, E., & Akcayol, M. A. (2016). A Comprehensive Survey for Sentiment Analysis Tasks Using Machine Learning Techniques. IEEE.
Bird, S., Klein, E., & Edward Loper. (2009). Natural Language Processing with Python.
Chawla, N. V, Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. In Journal of Artificial Intelligence Research (Vol. 16).
Darwis, D., Siskawati, N., & Abidin, Z. (2021). Penerapan Algoritma Naive Bayes untuk Analisis Sentimen Review Data Twitter BMKG Nasional. Jurnal TEKNO KOMPAK, 15(1), 131–145.
Han, H., Wang, W.-Y., & Mao, B.-H. (2005). LNCS 3644 - Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning. In LNCS (Vol. 3644).
Hasibuan, M. S., & Serdano, A. (2022). Analisis Sentimen Kebijakan Pembelajaran Tatap Muka Menggunakan Support Vector Machine dan Naive Bayes. JRST (Jurnal Riset Sains Dan Teknologi), 6(2), 199. https://doi.org/10.30595/jrst.v6i2.15145
Jordan, M. I., & Mitchell, T. M. (2015). Machine learning:Trends, perspectives, and prospects. Science, 349(6245), 253–255. https://doi.org/10.1126/science.aac4520
Joshi, M., Das, D., Gimpel, K., & A. Smith, N. (2010). N10-1038. Human Language Technologies, 293–296.
Liu, B. (2020). Sentiment Analysis Essentials Sentiment Analysis: Mining Opinions, Sentiments, and Emotions.
Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093–1113. https://doi.org/10.1016/j.asej.2014.04.011
Powers, D. M. W., & Ailab. (n.d.). EVALUATION: FROM PRECISION, RECALL AND F-MEASURE TO ROC, INFORMEDNESS, MARKEDNESS & CORRELATION.
Rennie, J. D. M., Shih, L., Teevan, J., & Karger, D. R. (n.d.). Tackling the Poor Assumptions of Naive Bayes Text Classifiers.
Robertson, S. (2004). Understanding inverse document frequency: On theoretical arguments for IDF. Journal of Documentation, 60(5), 503–520. https://doi.org/10.1108/00220410410560582
Sailunaz, K., & Alhajj, R. (2019). Emotion and sentiment analysis from Twitter text. Journal of Computational Science, 36. https://doi.org/10.1016/j.jocs.2019.05.009
Ullah, A., Zhang, Q., & Ahmed, M. (2021). The influence of intellectual property rights protection on contribution efforts of participants in online crowdsourcing contests. Computers in Human Behavior, 123. https://doi.org/10.1016/j.chb.2021.106869
Yadav, A., & Vishwakarma, D. K. (2020). Sentiment analysis using deep learning architectures: a review. Artificial Intelligence Review, 53(6), 4335–4385. https://doi.org/10.1007/s10462-019-09794-5
Published
How to Cite
Issue
Section
The Authors submitting a manuscript do so on the understanding that if accepted for publication, copyright of the article shell be assigned to Development Innovation: Jurnal Kelitbangan (JIP) , Balitbangda Provinsi Lampung as publisher of the journal.
Copyright encompasses exclusive rights to reproduce and deliver the article in all form and media, including reprints, photographs, microfilms and any other similar reproductions, as well as translations, the reproduction of any part of this journal, its storeage in databases and its transmission by any form or media. such as electronic, electrostatic and mechanical copies, photocopies, recordings, magnetic media, etc.
