The Mission

The mission of this project is to create a fast, student‑friendly feedback ecosystem that strengthens teaching quality through real‑time, data‑driven insights. Instead of relying on end‑of‑year evaluations that arrive too late to benefit current students, the project aims to capture immediate, authentic reactions after each lecture and transform them into actionable guidance for lecturers. By combining simple feedback collection with automated analysis, the project empowers educators to adapt their teaching quickly, improve clarity, and address learning gaps before they widen. Ultimately, the mission is to build a continuous improvement loop that enhances student engagement, supports instructors, and elevates the overall learning experience.

The Challenge

Universities face chronically low response rates on traditional course evaluations, especially when feedback is collected long after the lecture has taken place. This creates several unmet needs: -- Students rarely benefit from the feedback they provide because improvements are implemented only in the next academic year. -- Lecturers lack timely insight into whether students understood the core concepts of a lecture, which topics caused confusion, or how engaging the session felt. -- Institutions miss opportunities to make data‑driven decisions that could improve teaching quality and student satisfaction. -- The result is a disconnect students want clearer explanations and more engaging lectures, while teachers want to know what to revisit — but the current system delivers this information too late and with too little participation to be useful.

The solution

The project proposes a lightweight, lecture‑by‑lecture feedback system that captures student sentiment immediately after each class. The solution has three core components: A short, relatable feedback form delivered right after the lecture, using casual language students naturally use (“amazing,” “manageable,” “terrible,” etc.) to increase response rates. An open field for students to list concepts they did not understand, giving lecturers direct visibility into learning gaps. An AI‑powered analysis pipeline that clusters comments into lecture subtopics, builds a contingency table, and performs statistical tests to identify which topics are most strongly associated with negative or positive sentiment. This produces a prioritized list of concepts that need clarification, enabling lecturers to adjust their next tutorial or lecture immediately. The system closes the feedback loop, ensuring students benefit from their own feedback and instructors receive actionable insights in real time.