Detecting Students at Risk: Adventures in AI

ID: 53641 Type: Virtual Paper
  1. Owen Hall, Jr., Pepperdine University, United States

Identifying students at academic risk early in the matriculation process, especially online students, is on ongoing challenge. The evidence to date suggests that early invention can have a positive impact on student learning performance. One very telling variable in this regard is freshman performance. Current date suggests that nearly one-half of United States universities are experiences a first-year student attrition rate of 25 percent. Time is often the essence since waiting until midterm exam results to intervene can often prove problematic. In this regard, web-based learning management systems (LMS) provide an effective vehicle for not only modifying content and pace, but also for incorporating addition assessment variables early in the assessment process. The data indicates that continuous assessment encourages student engagement, which is turn enhances student learning outcomes. This is particularly true for online programs where a sense of isolation is often the norm. Specifically, providing continuous performance metrics (e.g., weekly quizzes) as well as monitoring the extent of student engagement within the LMS can help identify those students that may require additional assistance. The purpose off the presentation is to highlight the growing opportunities for using AI in detecting students at risk and outlining effective intervention strategies.

Topics

Conference attendees are able to comment on papers, view the full text and slides, and attend live presentations. If you are an attendee, please login to get full access.