New Software Stops Online Dropouts

New Software Stops Online Dropouts

Online training programs such as MOOCs are highly popular, yet suffer from high rates of student dropouts - probably because they're often free and don't require in-person attendance. 

At last week's International Conference on Artificial Intelligence in Education, MIT researchers demonstrated a dropout prediction model which can help predict which students will drop out of the next offering in a series of online courses. 

Veeramachaneni and Boyer's first step was to develop a set of variables that would allow them to compare data collected during different offerings of the same course - or, indeed, offerings of different courses. There are huge numbers of factors involved in whether or not a student completes a course, such as the student's motivation and which days of the week the student is able to dedicate to the course.

The team hope that better understanding the complexities of why a student drops out from a course will help prevent future dropouts and better shape the future of online education.

Current solutions to the issue of MOOC dropout rates include making courses-self-paced rather than imposing deadlines, email reminders to complete assignments, inserting more interactive elements to the course material, driving the importance of cohort bonding through discussion forums and so on. 

Join The Discussion