GPT-4o: Analysis of Natural Human-Computer Interaction and Social Effects of Generative Artificial Intelligence by Text Mining Method

Year 2025, Volume: 8 Issue: 2, 101 - 115

Cemal Yüksel

Abstract

The rapid development of artificial intelligence technologies has brought significant innovations in the field of natural language processing. This study analyses the technical features and social implications of the GPT 4o model developed by OpenAI. In the research, the effects of this model on human-computer interaction, social acceptance of artificial intelligence and ethical issues are discussed. Within the scope of the study, 90,016 user comments obtained from the YouTube platform were analysed using the DistilBERT and BerTopic model. According to the results of the analysis, 40.5% of the comments were neutral, 33.7% were positive and 25.8% were negative. Topic modelling analyses with BerTopic revealed that topics such as the future of AI, GPT integration and social benefits were discussed intensively. When the performance metrics of the model were evaluated, topic consistency was calculated as 0.429 and topic diversity as 0.817. The findings show that users generally have a positive approach, but ethical issues such as the potential of AI to spread misinformation and data privacy are also among the important concerns. In conclusion, this study aims to contribute to future research by providing guidance for responsible and effective use of AI technologies.

Keywords

ChatGPT , GPT-4o , Natural Language Processing , Human-Computer Interaction , Text Mining

References

• Abdullah, M., Madain, A., & Jararweh, Y. (2022). Chatgpt: Fundamentals, applications and social impacts. In 2022 Ninth International Conference on Social Networks Analysis, Management and Security (SNAMS) (pp. 1–8). IEEE.
• Altman, S. (2024, May 7). im-a-good-gpt2-chatbot [Tweet]. Twitter. Retrieved May 14, 2024, from https://twitter.com/sama/status/1787222050589028528
• Bai, L., Liu, X., & Su, J. (2023). ChatGPT: The cognitive effects on learning and memory. Brain‐X, 1(3), e30.
• Biswas, S. S. (2023). Role of ChatGPT in public health. Annals of Biomedical Engineering, 1–2.
• Bárcena Ruiz, G., de Jesús Gil, R. (2024). BERT Transformers Performance Comparison for Sentiment Analysis: A Case Study in Spanish. In: Rocha, Á., Adeli, H., Dzemyda, G., Moreira, F., Poniszewska-Marańda, A. (eds) Good Practices and New Perspectives in Information Systems and Technologies. WorldCIST 2024. Lecture Notes in Networks and Systems, vol 989. Springer, Cham. https://doi.org/10.1007/978-3-031-60227-6_13
• Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., ... & Amodei, D. (2020). Language models are few-shot learners. arXiv preprint arXiv:2005.14165.
• Chandra, S., Shirish, A., & Srivastava, S. C. (2022). To be or not to be… human? Theorizing the role of human-like competencies in conversational artificial intelligence agents. Journal of Management Information Systems, 39(4), 969-1005.
• Egger, R., & Yu, J. (2022). A topic modeling comparison between lda, nmf, top2vec, and bertopic to demystify twitter posts. Frontiers in sociology, 7, 886498.
• Edwards, B. (2024, May 13). Before launching, GPT-4o broke records on chatbot leaderboard under a secret name. Ars Technica. Retrieved May 17, 2024, from https://arstechnica.com/information-technology/2024/05/gpt-4o-broke-records-on-chatbot-leaderboard/
• Geach, P. T. (1973). Omnipotence. Philosophy, 48(183), 7-20.
• George, A. S., & George, A. H. (2023). A review of ChatGPT AI's impact on several business sectors. Partners Universal International Innovation Journal, 1(1), 9-23.
• Grootendorst, M. (2020). BERTopic: Leveraging BERT and c-TF-IDF to create easily interpretable topics. arXiv preprint arXiv:2008.03979.
• Haque, M. U., Dharmadasa, I., Sworna, Z. T., Rajapakse, R. N., & Ahmad, H. (2022). "I think this is the most disruptive technology": Exploring sentiments of ChatGPT early adopters using Twitter data. arXiv preprint arXiv:2212.05856.
• Hietalahti, J. (2021). Laughing with machines. The European Journal of Humour Research, 9(2), 154-171.
• Koonchanok, R., Pan, Y., & Jang, H. (2024). Public attitudes toward ChatGPT on Twitter: sentiments, topics, and occupations. Social Network Analysis and Mining, 14(1), 106.
• Korkmaz, A., Aktürk, C., & Talan, T. (2023). Analyzing the user’s sentiments of ChatGPT using Twitter data. Iraqi Journal for Computer Science and Mathematics, 4(2), 202–214.
• Kuzdeuov, A., Mukayev, O., Nurgaliyev, S., Kunbolsyn, A., & Varol, H. A. (2024, February). ChatGPT for visually impaired and blind. In 2024 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (pp. 722-727). IEEE.
• Leiter, C., Zhang, R., Chen, Y., Belouadi, J., Larionov, D., Fresen, V., & Eger, S. (2023). ChatGPT: A meta-analysis after 2.5 months. arXiv preprint arXiv:2302.13795.
• Lund, H. H. (2004). Modern artificial intelligence for human-robot interaction. Proceedings of the IEEE, 92(11), 1821-1838.
• Nehaniv, C. L., & Dautenhahn, K. (2001). Imitation in natural and artificial systems. Cybernetics & Systems, 32(1-2), 1-10.
• OpenAI. (2024). Hello GPT-4o. [Online] Available at: https://openai.com/index/hello-gpt-4o/
• Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I. (2018). Improving language understanding by generative pre-training. OpenAI.
• Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., ve diğerleri. (2019). Language models are unsupervised multitask learners. OpenAI.
• Shoufan, A. (2023). Exploring students’ perceptions of ChatGPT: Thematic analysis and follow-up survey. IEEE Access.
• Sudirjo, F., Diawati, P., Riady, Y., Ausat, A. M. A., & Suherlan, S. (2023). The role of chatgpt in enhancing the information search and decision-making process of travellers. Jurnal Minfo Polgan, 12(1), 500-507.
• Supriyadi, E., & Kuncoro, K. S. (2023). Exploring the future of mathematics teaching: Insight with ChatGPT. Union: Jurnal Ilmiah Pendidikan Matematika, 11(2), 305-316.
• Tounsi, A., Elkefi, S., & Bhar, S. L. (2023). Exploring the reactions of early users of ChatGPT to the tool using Twitter data: Sentiment and topic analyses. In 2023 IEEE International Conference on Advanced Systems and Emergent Technologies (IC ASET) (pp. 1-6). IEEE. https://ieeexplore.ieee.org/abstract/document/10150870
• Zeff, M. (2024, May 7). Powerful New Chatbot Mysteriously Returns in the Middle of the Night. Gizmodo. Retrieved May 17, 2024, from https://gizmodo.com/powerful-new-chatbot-mysteriously-returns-1849968290
• Karimi, R., Baghalzadeh Shishehgarkhaneh, M., Moehler, R. C., & Fang, Y. (2024). Exploring the Impact of Social Media Use on Team Feedback and Team Performance in Construction Projects: A Systematic Literature Review. Buildings, 14(2), 528.
• Leong, C., Pan, S. L., Bahri, S., & Fauzi, A. (2019). Social media empowerment in social movements: power activation and power accrual in digital activism. European Journal of Information Systems, 28(2), 173-204.
• Lobera, J., & Portos, M. (2021). Decentralizing electoral campaigns? New-old parties, grassroots and digital activism. Information, Communication & Society, 24(10), 1419-1440.
• Minocher, X. (2019). Online consumer activism: Challenging companies with Change.org. New Media & Society, 21(3), 620-638.
• Mousavi, R., Johar, M., & Mookerjee, V. S. (2020). The voice of the customer: Managing customer care in Twitter. Information Systems Research, 31(2), 340-360.
• Mutlu, E. (1991). Televizyonu Anlamak. İstanbul: Gündoğan Yayınları.
• Napoli, P. M. (2011). Audience evolution: New technologies and the transformation of media audiences. Columbia University Press.
• Nielsen. (2023). 2023 Nielsen Annual Marketing Report. Nielsen. https://sproutsocial.com/insights/data/harris-insights-report-2023/ (Erişim Tarihi: 30 Haziran 2024)
• Ouma, N. C. (2013). Effects of Social Media on Content of Local Television Programs in Kenya: a Case Study of Citizen Tv's Gospel Sunday Show (Doctoral dissertation, University of Nairobi).
• Özkula, S. M., Reilly, P. J., & Hayes, J. (2023). Easy data, same old platforms? A systematic review of digital activism methodologies. Information, Communication & Society, 26(7), 1470-1489.
• Pérez-Torres, V. (2024). Social media: a digital social mirror for identity development during adolescence. Current Psychology, 1-11.
• Waddell, T. F., & Sundar, S. S. (2017). #thisshowsucks! The overpowering influence of negative social media comments on television viewers. Journal of Broadcasting & Electronic Media, 61(2), 393-409.
• Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review, 55(7), 5731-5780.
• Zaheroghli, M. N. (2023). Türk dizi ihracatının Türk ürünlerine yönelik satın alma niyeti açısından incelenmesi = Examination of Turkish TV series exports in terms of purchasing intention for Turkish products (Master's thesis, Sakarya Üniversitesi).