Changing the recent past to reduce ongoing dropout: an early learning analytics intervention for an online statistics course.

Practitioners of the statistics course embedded in a computer science programme at a fully online university were concerned with the high dropout rate. In the academic year 2018–19, they decided to carry out a two-phase project in order to address this issue. In the first phase, an early classifier to identify students at risk of dropping out of the 2018–19 statistics course was determined. The second phase was planned to design and implement an early intervention based on the results of the first phase. This article presents the analysis of this intervention. In the 2019–20 online statistics course, 35 students did not submit the first few quizzes before the respective deadlines. They were the target of this intervention, which gave them the chance to change their recent past by submitting the unsubmitted quizzes. Students were encouraged to change by means of an email message. The aim of the intervention was to reduce the dropout rate among the targeted students. Our analysis also includes the students' perception of the intervention collected via a set of interviews. The results show that the intervention clearly had a beneficial effect for some students. [ABSTRACT FROM AUTHOR]