Knowledge Discovery Based on Sentiment Analysis of Public Perceptions About Generative AI on X

Muammar Ramadhani Maulizidan, Ken Ditha Tania

Abstract

Public discourse surrounding Generative Artificial Intelligence (GenAI) reflects diverse attitudes ranging from optimism to ethical concern, particularly as these technologies become increasingly discussed in educational contexts. This study examines public perceptions of GenAI on the social media platform X using a knowledge discovery approach that integrates multiple topic modeling techniques and Aspect-Based Sentiment Analysis (ABSA). A total of 111,675 English-language tweets collected between June 23, 2024, and June 23, 2025, were analyzed using five topic modeling methods BERTopic, Top2Vec, LDA, LSA, and NMF to identify dominant discussion themes and evaluate topic coherence. Sentiment toward specific GenAI aspects was subsequently examined using ABSA to capture fine-grained public attitudes. The results indicate that topics related to ethics and creativity are predominantly associated with negative sentiment, while innovation and cloud-related discussions show higher levels of positive sentiment. Education-related topics are largely characterized by neutral sentiment, suggesting exploratory and informational discourse. These findings highlight the importance of addressing ethical awareness, trust, and AI literacy in informatics education. By combining multi-model topic analysis with aspect-level sentiment interpretation, this study provides methodological insights and empirical evidence to support responsible GenAI integration in educational contexts.

Keywords

Aspect-Based Sentiment Analysis; Generative Artificial Intelligence; Knowledge Discovery; Social Media X; Topic Modeling

Full Text:

PDF

References

Agustina, D. A., Subanti, S., & Zukhronah, E. (2021). Implementasi Text Mining Pada Analisis Sentimen Pengguna Twitter Terhadap Marketplace di Indonesia Menggunakan Algoritma Support Vector Machine. Indonesian Journal of Applied Statistics, 3(2), 109–116. https://doi.org/10.13057/ijas.v3i2.44337

Ariannor, W., Alshalwi, S. M. A. B., & Susarianto, B. (2024). Sentiment Analysis of Netizens on Constitutional Court Rulings in the 2024 Presidential Election. IJIE (Indonesian Journal of Informatics Education), 8(2), 90–98. https://doi.org/10.20961/ijie.v8i2.94614

Arowosegbe, A., Alqahtani, J. S., & Oyelade, T. (2024). Perception of generative AI use in UK higher education. Frontiers in Education, 9, 1463208. https://doi.org/10.3389/feduc.2024.1463208

Desai, D. R., & Riedl, M. (2024). Between Copyright and Computer Science: The Law and Ethics of Generative AI. arXiv. https://arxiv.org/abs/2408.08272

Doogan, C., & Buntine, W. (2021). Topic Model or Topic Twaddle? Re-evaluating Semantic Interpretability Measures. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 3824–3848. https://doi.org/10.18653/v1/2021.naacl-main.300

Egger, R., & Yu, J. (2022). A Topic Modeling Comparison Between LDA, NMF, Top2Vec, and BERTopic to Demystify Twitter Posts. Frontiers in Sociology, 7, 886498. https://doi.org/10.3389/fsoc.2022.886498

Geiger, C. (2024). Elaborating a Human Rights-Friendly Copyright Framework for Generative AI. IIC - International Review of Intellectual Property and Competition Law, 55(7), 1129–1165. https://doi.org/10.1007/s40319-024-01481-5

Ghimire, A., & Edwards, J. (2024). Generative AI Adoption in Classroom in Context of Technology Acceptance Model (TAM) and the Innovation Diffusion Theory (IDT). arXiv. http://arxiv.org/abs/2406.15360

Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv. http://arxiv.org/abs/2203.05794

Hasan Emon, M. M. (2023). Insights into technology adoption: A systematic review of framework, variables and items. Information Management and Computer Science, 6(2), 55–61. https://doi.org/10.26480/imcs.02.2023.55.61

Ibrahim, F., Münscher, J.-C., Daseking, M., & Telle, N.-T. (2025). The technology acceptance model and adopter type analysis in the context of artificial intelligence. Frontiers in Artificial Intelligence, 7, 1496518. https://doi.org/10.3389/frai.2024.1496518

Islam, G., & Greenwood, M. (2024). Generative Artificial Intelligence as Hypercommons: Ethics of Authorship and Ownership. Journal of Business Ethics, 192(4), 659–663. https://doi.org/10.1007/s10551-024-05741-9

Karas, B., Qu, S., Xu, Y., & Zhu, Q. (2022). Experiments with LDA and Top2Vec for embedded topic discovery on social media data—A case study of cystic fibrosis. Frontiers in Artificial Intelligence, 5, 948313. https://doi.org/10.3389/frai.2022.948313

Krishnan, A. (2023). Exploring the Power of Topic Modeling Techniques in Analyzing Customer Reviews: A Comparative Analysis. arXiv. http://arxiv.org/abs/2308.11520

Kristianto, K., Ramadhan, A. B., & Marsetyo, F. D. (2021). Media Sosial dan Connective Action: Studi Kasus Penggunaan Twitter sebagai Ruang Solidaritas selama Pandemi COVID-19. Journal of Social Development Studies, 2(1), 1–13. https://doi.org/10.22146/jsds.1037

Miyazaki, K., Murayama, T., Uchiba, T., An, J., & Kwak, H. (2023). Public Perception of Generative AI on Twitter: An Empirical Study Based on Occupation and Usage. arXiv. http://arxiv.org/abs/2305.09537

Novalia, V., Ditha Tania, K., Meiriza, A., & Wedhasmara, A. (2024). Knowledge Discovery of Application Review Using Word Embedding’s Comparison with CNN-LSTM Model on Sentiment Analysis. 2024 International Conference on Electrical Engineering and Computer Science (ICECOS), 234–238. https://doi.org/10.1109/ICECOS63900.2024.10791113

Nurlanuly, A. T. (2025). Sentiment analysis of texts from social networks based on machine learning methods for monitoring public sentiment. arXiv. http://arxiv.org/abs/2502.17143

Pranatawijaya, V. H., Sari, N. N. K., Rahman, R. A., Christian, E., & Geges, S. (2024). Unveiling User Sentiment: Aspect-Based Analysis and Topic Modeling of Ride-Hailing and Google Play App Reviews. Journal of Information Systems Engineering and Business Intelligence, 10(3), 328–339. https://doi.org/10.20473/jisebi.10.3.328-339

Pratiwi, M. D., & Tania, K. D. (2025). Knowledge Discovery Through Topic Modeling on GoPartner User Reviews Using BERTopic, LDA, and NMF. Journal of Applied Informatics and Computing, 9(1), 1–7. https://doi.org/10.30871/jaic.v9i1.8782

Rahimi, H., Hoover, J. L., Mimno, D., Naacke, H., Constantin, C., & Amann, B. (2023). Contextualized Topic Coherence Metrics. arXiv. https://doi.org/10.48550/arXiv.2305.14587

Rüdiger, M., Antons, D., Joshi, A. M., & Salge, T.-O. (2022). Topic modeling revisited: New evidence on algorithm performance and quality metrics. PLOS ONE, 17(4), e0266325. https://doi.org/10.1371/journal.pone.0266325

Sengar, S. S., Hasan, A. B., Kumar, S., & Carroll, F. (2024). Generative artificial intelligence: a systematic review and applications. Multimedia Tools and Applications, 84(21), 23661–23700. https://doi.org/10.1007/s11042-024-20016-1

Singh, S., & Strzelecki, A. (2025). Academics as adopters of generative AI: an application of diffusion of innovations theory. Education and Information Technologies. Advance online publication. https://doi.org/10.1007/s10639-025-13835-8

Suhendra, S., & Selly Pratiwi, F. (2024). Peran Komunikasi Digital dalam Pembentukan Opini Publik: Studi Kasus Media Sosial. Iapa Proceedings Conference, 293–305. https://doi.org/10.30589/proceedings.2024.1059

Sujana, Y. (2024). A Comparative Study of Machine Learning Models for Sentiment Analysis of Dana App Reviews. IJIE (Indonesian Journal of Informatics Education), 7(2). https://doi.org/10.20961/ijie.v7i2.93132

Utami, H. (2022). Analisis Sentimen dari Aplikasi Shopee Indonesia Menggunakan Metode Recurrent Neural Network. Indonesian Journal of Applied Statistics, 5(1), 31–41. https://doi.org/10.13057/ijas.v5i1.56825

Zharif Mustaqim, I., Melani Puspasari, H., Tri Utami, A., Syalevi, R., & Ruldeviyani, Y. (2024). Assessing public satisfaction of public service application using supervised machine learning. IAES International Journal of Artificial Intelligence (IJ-AI), 13(2), 1608–1618. https://doi.org/10.11591/ijai.v13.i2.pp1608-1618

DOI: https://doi.org/10.20961/ijie.v9i2.107758