Deploy LLM-based slide feedback dashboards before oral presentations so students can iteratively revise slides when teacher feedback is infeasible at scale¶

Strategy · All strategies
Evidence · no claims cited

Description¶

The article recommends combining LLM-based analysis with Learning Analytics dashboards to deliver timely, rubric-aligned formative feedback on slides before the oral presentation, addressing the problem that feedback "is often limited to a final performance review and therefore arrives too late for students to revise their visual materials beforehand". Teachers configure rubrics, manage cohorts, and monitor engagement through activity logs, while students upload, review feedback, and resubmit improved versions.

Design Implications¶

Context¶

Requirements¶

• Teacher-defined evaluation rubrics; a deployment setting where students can upload slide decks prior to presenting; capacity to handle peak submission periods via asynchronous processing

Constraints¶

• Evidence to date is a single pilot; the article states that pedagogical impact, including whether iterative use leads to measurable improvements in slide quality and final presentation performance, remains to be studied systematically

Target Learners¶

• undergraduate students in large higher-education classes

Target Learning Goals¶

• timely formative feedback on presentation slides and iterative slide improvement

Related Strategies¶

• Use overlapping multi-slide windows and deck-level reconciliation rather than per-slide generation

Examples¶

-

Key Sources¶

• Alvaro Becerra, Diego Gomez, Ruth Cobos. (2026). AISSA: Implementation and Deployment of an AI-based Student Slides Analysis tool for Academic Presentations. LASI Spain 26: Learning Analytics Summer Institute Spain 2026. https://orcid.org/0009-0003-7793-2682