Interdisciplinary approach to problematic features of the use of artificial intelligence among university students

This study looks at the problems that come with university students quickly adopting artificial‑intelligence (AI) tools. It proposes a cross‑disciplinary machine‑learning system that can spot and model risky usage patterns. As generative AI and automated help become common in higher education, it is important to understand how they affect students’ behavior, thinking, and ethics. The proposed method combines three parts: – **Educational data mining** – collecting data on how students use AI tools. – **Behavioral‑psychology features** – measuring things like reliance on the tool and how much thinking is offloaded. – **Predictive modeling** – building models that can flag potential issues. First, the system extracts and cleans a multi‑dimensional set

of features. These include how often a student interacts with the AI, how complex the tasks are, and when the tool is used. Using these features, supervised classification models are trained to sort students into different engagement levels. Next, unsupervised clustering is used to uncover hidden groups of behavior across various majors. This helps reveal common “behavioral archetypes” that might not be obvious from the raw data. The models are judged with standard metrics—precision, recall, and F1‑score—to make sure they reliably detect unusual usage patterns. Overall, the research offers a clear way for universities to monitor AI use. It gives data‑driven insights that can help balance AI assistance with independent

learning. The results can also guide the creation of ethical policies and adaptive support strategies in today’s educational environment.

Message: Hi FE, I need help with “Interdisciplinary approach to problematic features of the use of artificial intelligence among university students” in “Computer Science & Engineering”