October 26, 2014

Use of analytics for early intervention with ‘at-risk’ students

Listen with webReader

© Bowen Island Community School

Grush, M. (2011) Monitoring the PACE of Student Learning: Analytics at Rio Salado College Campus Technology, December 14

This article looks at the use of learning analytics at Rio Salado College, Arizona, where all 41,000 students take online courses. It has instituted a Progress and Course Engagement (PACE) system for automated tracking of student progress–with intervention as needed. They found that there are three main predictors of success:

  • the frequency of a student logging into a course;
  • site engagement–whether they read or engage with the course materials online and do practice exercises and so forth; and
  • how many points they are getting on their assignments.

They claim they can predict, after the first week of a course, with 70 percent accuracy, whether any given student will complete the course successfully (with a grade of “C” or better). The PACE system enables them to identify the level of risk for every student in a course, which helps to focus instructor, advisor, and other institutional resources on quickly helping the ones who are most at risk.

There is a good deal more in the article about the potential of learning analytics in post-secondary education.

 

Comments

  1. Tony:
    I also believe that analytics might (and should) introduce a major advance for teaching and learning, especially online. This potential is dubious in the PACE system as you describe. The PACE model of learning and analytics seem to mechanize learning, numbing down the learner: arguably making “artificial intelligence’ true for human beings. Students engaged in such learning activities arguably become increasingly roboticized and mechanized in their response, and less innovative and able to create and construct new ways of problem solving and innovation.

    I have been working on rubrics to identify learning process and advances, especially in online collaborations such as education.

    Innovation, problem solving and knowledge building are not “predictable”. Predictability of content is based on replication of what has already been deemed “the correct answer”.

    Another aspect of prediction is not about outcomes but completion rates; Hiltz (1990; 1994) found that self-selection predicted successful completion of an online collaborative learning course.

    Cheers,
    Linda

Trackbacks

Speak Your Mind

*