Conversational AI-Driven Coach
A personalized AI-driven coach that enhances student performance through adaptive learning strategies, combining Tutor-based and Socratic-based coaching for improved engagement, goal attainment, and long-term learning success.
Factsheet
- Schools involved Business School
- Institute(s) Institute for Digital Technology Management
- Strategic thematic field Thematic field "Humane Digital Transformation"
- Funding organisation Others
- Duration (planned) 01.01.2025 - 31.01.2026
- Head of project Prof. Dr. Roman Rietsche
- Project staff Bithiah Yuan
- Keywords AI Coaching, Digital Learning, Adaptive Tutoring, Large Language Models, Personalized Learning, Student Engagement, Socratic Questioning, Tutor-Based Coaching, Educational Technology, Behavioral Chang
Situation
Students in specialized study programs have diverse academic backgrounds, leading to varying prior knowledge and preparedness. Educators struggle to provide personalized support due to time constraints and cognitive overload. Traditional goal-setting strategies are effective in enhancing focus, motivation, and efficiency but are difficult to scale. Large Language Models (LLMs) offer a scalable solution, but research is needed to compare different coaching strategies (Tutor-based vs. Socratic-based) to optimize engagement and learning outcomes. This project investigates these strategies in an AI-driven digital coaching environment.
Course of action
The project employs a Human-Computer Interaction and Information Systems methodology with user-centered design, generative AI techniques, and experimental evaluation. Key phases include: 1. Development: Design and implement Tutor-based and Socratic-based AI agents. 2. Experiment: Conduct controlled studies comparing engagement, cognitive load, and goal attainment. 3. Longitudinal Study: Evaluate long-term impact on student retention, self-regulation, and academic performance. 4. Data Analysis & Publication: Use multi-level modeling to assess results and disseminate findings in academic journals and CHI conferences.
Result
Expected outcomes include empirical insights into the effectiveness of different dialogue strategies in digital coaching. The research will contribute to a theoretical framework for AI-driven coaching and personalized learning. The project will develop an adaptive coaching system that enhances student motivation, engagement, and long-term success. Findings will be published in high-impact academic journals and contribute to the future of AI-powered education.
Looking ahead
The AI coaching system will be integrated into higher education platforms, such as Moodle, to provide scalable, personalized tutoring support. Further studies will explore adaptive AI coaching in different disciplines and workforce upskilling. The research collaboration between Bern University of Applied Sciences, University of St. Gallen, and University of Pennsylvania will continue to expand, refining AI-driven coaching methodologies for real-world applications.
