Enhancing Student Feedback Using Predictive Models in Visual Literacy Courses

In the evolving landscape of educational technology, data visualization plays a pivotal role in higher education. While peer review is an established pedagogical tool that actively engages students, its long-term effectiveness, particularly when integrated with data-driven predictive modeling for analyzing student comments, has not been empirically validated, especially in the context of data visualization courses. This study aims to fill this gap by employing Naïve Bayes modeling to analyze peer review data from an undergraduate visual literacy course over a five-year period (2017–2022). Building on the research of Friedman and Rosen [1], as well as Beasley et al. [2], our study not only reaffirms the utility of Naïve Bayes modeling in analyzing student comments, particularly focusing on parts of speech with nouns as the prominent category but also explores its application in enhancing the peer review process. A key finding is the emphasis on the ‘lie factor’ in students' comments when using the visual peer review rubric, highlighting areas for potential course content adaptation and instructional refinement. Comparing the Naïve Bayes model with Beasley's approach, we find that while both methodologies aid instructors in mapping classroom dynamics, the Naïve Bayes model offers a more detailed framework for predictive analysis. Our findings suggest that predictive modeling, as a tool to assess student comments, can provide novel insights into visual peer review. This could lead to impactful changes in course content, project modifications, and rubric enhancements, ultimately benefiting student learning and engagement in visual literacy courses.