Using Passive Sensing to Assess the Impact of Real-Time Discrimination against Women and Underrepresented Minorities in Engineering

University Of Washington, Seattle WA

Investigators

Abstract

Increasing diversity in engineering and computer science has been a goal that remains elusive. Despite significant efforts, underrepresented minorities received only 16.1% and women received only 21.9% of engineering degrees in 2018. The reasons for these low numbers are complex and multifaceted and discrimination is an important factor in why students from these groups leave engineering. The goal of this research is to develop a holistic understanding of the impact of discrimination on historically underrepresented engineering students. In this era of big data and readily available technology such as mobile phones and wearables, a comprehensive change in how data about the college student experience are collected and assessed is possible. One can now move from lab to field, connect action to behavior, and collect longitudinal data. This, in turn, makes it possible to understand bias and its impact on engineering education in new ways: By complementing self-reports with passive data collection, big data can be used to create an image of behavior while learning about specific challenges underrepresented minority and female engineering students face. The project will result in a uniquely powerful longitudinal data set, which captures real-time changes in student experiences and allows study of the impact of discrimination at scale across a variety of contexts. The project will quantify the scope, direction, and longitudinal impact on behavior and link this to long-term outcomes such as GPA and retention. This ability to connect behavior to experience in the field was lacking in past studies of discrimination. Analytic techniques capable of capturing both individual variance and looking at unequal numbers of observations, such as hierarchical linear modeling, are required due to the large sample (N=200/year) and number of variables. The data are collected at a large public university and will be most applicable to similar programs at similar institutions. The research will support policy making and intervention design in engineering programs. The ultimate goal is to diversify the pool of engineering students, which will be of direct benefit to society by increasing representation and the range of perspectives engaged in the engineering and computer science workforce. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.