Improving the Learning Experiences of First-Year Computer Science Students with Empathetic IDEs

Abstract

Computer science has the highest dropout rate among undergraduate STEM degree programs. This is especially concerning, given that computer science-related jobs are projected to grow 12% in the next six years. One contributing factor is that media representations of computer science can lead underrepresented groups to perceive themselves as unfit for the discipline, and ultimately to drop out. To address this concern, I propose an empathetic IDE model that uses affective computing technologies to promote empathy among computer science students. A quasi-experimental research design will be used to evaluate the model's effectiveness in fostering a supportive community between instructors and students. By leveraging emotional learning process data as a form of constant feedback to both instructors and students, this research can gain new insights into how to improve learning environments for computer science students with or without affective computing technologies.