Recent advances in artificial intelligence (AI) have significantly expanded the possibilities for educational research, especially in analyzing complex social interactions within classroom environments more efficiently. In my talk, I focus on AI-based approaches for classifying teachers’ verbal and nonverbal behaviors. Specifically, I highlight the use of computer vision techniques to analyze nonverbal immediacy, and the application of large language models (LLMs) to assess motivational messages delivered by teachers. I will also discuss the potential and limitations of these AI-driven methods, along with their ethical implications and relevance for educational practice. The talk provides an overview of our research conducted at the Science of Intelligence research center (2019–2025; www.scienceofintelligence.de) as well as ongoing work in my research group, Research on Instruction and Schools, at the University of Potsdam, within the new DFG-funded project Motivate! (www.uni-potsdam.de/en/dfg-projekt-motiv)

Teams-link: teams.microsoft.com/l/meetup-join/19%3ameeting_ZDYwMTY0ZmQtNjkzYS00NjFlLWEzNzgtNWYzMTkzNzQ1YmM2%40thread.v2/0?context=%7b%22Tid%22%3a%22cc95de1b-97f5-4f93-b4ba-fe68b852cf91%22%2c%22Oid%22%3a%22b33f55d8-6202-46f8-a141-737715faff88%22%7d