Unlocking Student Voices: AI–Augmented Analysis for Institutional Advancement

Institutions collect vast amounts of qualitative student feedback that often remains underutilized due to analytical and financial challenges. This poster session presents a practical workflow that leverages Large Language Models (LLMs) and natural language processing to transform how we analyze student feedback at scale while maintaining methodological integrity. By combining AI’s processing power with human expertise, we employ a rigorous “human-in-the-loop” validation process that enables institutions to uncover valuable insights hidden in course evaluations, surveys, and discussion forums. This hybrid approach accelerates analysis cycles while ensuring ethical standards through robust data anonymization and privacy protocols. Join us to explore a responsible framework that turns qualitative data into evidence-based decisions, enabling greater responsiveness within educational environments. Attendees will gain practical strategies for implementing an LLM-augmented qualitative analysis workflow that enhances institutional decision-making without compromising research principles or student privacy.