Using AI-Enabled Divergence and Convergence Patterns as a Quantitative Artifact in Design Education

Abstract

Design education has traditionally relied heavily on physical integration as it involves a lot of hands-on work, group critiques, and collaborative projects, but the COVID-19 pandemic has forced many institutions to adapt to remote teaching and learning environments. This has created challenges for design educators who have had to find ways to evaluate students' progress in the absence of in-person interactions. In this paper, we are proposing a dashboard visualisation approach that helps educators to monitor the progression of the entire class of students using Artificial Intelligence (AI) by tracking a time-based evolution of a design statement. This approach uses various Natural Language Processing (NLP) models to produce stock-like charts which represent students' and student groups' progression through a series of divergence and convergence phases. These charts become a form of Design Artifact that allows educator(s) to gain a birds-eye view of the class and react to groups that may require assistance; at the same time it becomes a qualitative means of evaluation and comparison across students and groups. Towards the end, this paper also showcases a web-based platform that is publicly available using such methodology, a case study that applied so methodology and recommendation of future works possible.