Stephan Weibelzahl

On-line education is one of the most dynamic and potentially enriching forms of learning that exists today. However, attrition is a serious problem resulting in personal, occupational and financial implications for both students and academic institutions. Motivation to learn is affected by a student's self-efficacy, goal orientation, locus of control and perceived task difficulty. In the classroom teachers know how to motivate their students and how to exploit this knowledge to adapt or optimize their instruction when a student shows signs of demotivation. In online learning environments it is much more difficult to assess the level of motivation of the student and to have adaptive intervention strategies and rules of application to help prevent attrition. We have developed MotSaRT to support online facilitators in motivating learners. The design is informed by the Social Cognitive Theory constructs outlined above and a survey on motivation intervention strategies carried out with sixty on-line facilitators (lecturers/tutors). The survey results were analysed using a data mining algorithm (J48 decision trees) which resulted in a set of decision rules for recommending motivational strategies. For example: where a learner has low self efficacy, is disengaged motivationally, has an external locus of control and perceives the task as being very difficult, the most frequently recommended intervention strategies are (a) to review progress with the student at regular intervals, (b) explain the importance of and encourage student to maintain contact with facilitator, and (c) encourage peer-to-peer contact. The recommender tool, MotSaRT, has been developed based on these decision rules. Its functionality enables the facilitator to specify the learner's motivation profile. MotSaRT then recommends the most likely intervention strategies to increase motivation. A pilot study is currently being carried out using the MotSaRT tool.