Machine Learning Analysis of Problems Encountered by STEM Students from Underrepresented Groups During the Covid-19 Pandemic

Abstract

During the current Covid-19 pandemic, STEM students from underrepresented groups have been disproportionately affected. These include women in STEM degree programs, “first generation” students from non-academic families, students with a migration background, students with physical or psychological disabilities and students with children. A control group of university students who do not belong to any of the categories above was defined. This work presents concrete problems reported by students from underrepresented groups as ascertained during interviews. The interviews were first recorded as audio files and then transcribed using speech-recognition software. Transcripts from interviews were analyzed with machine learning methods in an to attempt to identify whether specific patterns of problems were experienced by members of one of the underrepresented groups, or whether the difficulties encountered were uniform across all types of student groups, including the control group. The problems identified in these interviews were compared and contrasted to those previously presented in published literature before the pandemic. These results will be used to define requirements for the design of future digitalization measures to specifically support university students from underrepresented groups.



Author Information
Anna Protisina, Nuremberg Institute of Technology, Germany
Beate Neumer, Nuremberg Institute of Technology, Germany
Patricia Brockmann, Nuremberg Institute of Technology, Germany

Paper Information
Conference: BCE2021
Stream: Higher education

This paper is part of the BCE2021 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window


Comments & Feedback

Place a comment using your LinkedIn profile

Comments

Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by amp21