AISSA: Implementation and Deployment of an AI-based Student Slides Analysis tool for Academic Presentations

Providing timely, actionable feedback on presentation slides is a major challenge in higher education, especially in large courses where instructors cannot review every deck before students present. To solve this, researchers from Universidad Autónoma de Madrid developed AISSA (AI-based Student Slides Analysis tool), a web-based system that combines large language models (specifically ChatGPT 5.2) with Learning Analytics dashboards. Students upload their slide decks prior to their oral presentation, and AISSA automatically analyzes both slide-level features and content using teacher-defined evaluation rubrics. The system outputs quantitative scores and detailed qualitative feedback, then surfaces everything through interactive dashboards for students and teachers.

AISSA was piloted with 46 undergraduate students in a real academic setting. Results showed the system is technically reliable, economically feasible, and perceived by students as genuinely useful for iterative slide improvement before their actual presentation. The study found that combining LLM-based analysis with analytics dashboards is a promising approach for scaling formative feedback on presentation slides — something that's particularly valuable for large classes where personalized instructor feedback is impractical. This could significantly reduce teacher workload while giving every student the same level of detailed guidance on their presentation materials.