Early Warning Systems for Attrition

The ability to identify students who might soon decide to drop out of a given academic program allows those in charge to not only understand the causes, but it also provides room for the development of early intervention systems to assist such students.

Based on work by: Everaldo Aguiar, Nitesh Chawla, Jay Brockman, G. Alex Ambrose, and Victoria Goodrich, University of Notre Dame

Intervention Types : Process, Software

Using data from the Notre Dame College of Engineering course sequence, investigators studied the frequency of entries in e-portfolios. Portfolio assignments were integrated with the traditional course deliverables as a means to guide students‘ reflections on their experiences in the program. Such e-portfolios were shown to be effective sources of data in building early warning systems that can identify at-risk students at very early stages of their academic life, giving educators the opportunity to intervene before such students drop out of STEM courses of study.

Conclusions and Lessons Learned

  • Measures of student engagement (such as student reflections on their learning experience in ePortfolios) can provide meaningful data about student learning and, in this study, persistence.

Cited References