@article{article_1677061, title={Exploring User Perceptions of ChatGPT: A Large-Scale Topic Modeling Analysis using LDA}, journal={Academic Platform Journal of Engineering and Smart Systems}, volume={13}, pages={120–130}, year={2025}, DOI={10.21541/apjess.1677061}, author={Kılınç, Murat and Ayaz, Ahmet}, keywords={ChatGPT, Latent Dirichlet Allocation, Topic Modeling, User Feedback}, abstract={Today, AI-based chatbots are widely used to improve the user experience and provide support in various areas. Especially advances in natural language processing (NLP) technologies have made these systems more intelligent and user-friendly. ChatGPT, developed by OpenAI, is one of the most popular applications in this field and serves millions of users. Users’ experiences with ChatGPT are of great importance in determining the strengths and weaknesses of the model. In this study, Latent Dirichlet Allocation (LDA) method was used to analyze user feedback on ChatGPT. The main themes of user experiences were revealed by analyzing 250,000 user comments obtained through data scraping techniques on Google Play with topic modeling techniques. In our study, data cleaning and preprocessing steps were first applied, and then the comments were analyzed with LDA techniques. As a result of the analysis, user comments were grouped under certain themes and the most prominent themes were technical problems, feature requests, academic use, service quality and functionality. These themes help to understand ChatGPT’s strengths and areas for improvement. For future studies, a more comprehensive evaluation by analyzing comments from different platforms is recommended.}, number={3}, publisher={Akademik Perspektif Derneği}