The ability to predict student performance in a course or program creates opportunities to improve educational outcomes. With effective performance prediction approaches, instructors can allocate resources and instruction more accurately. Research in this area seeks to identify features that can be used to make predictions, to identify algorithms that can improve predictions, and to quantify aspects of student performance. Moreover, research in predicting student performance seeks to determine interrelated features and to identify the underlying reasons why certain features work better than others. This working group report presents a systematic literature review of work in the area of predicting student performance. Our analysis shows a clearly increasing amount of research in this area, as well as an increasing variety of techniques used. At the same time, the review uncovered a number of issues with research quality that drives a need for the community to provide more detailed reporting of methods and results and to increase efforts to validate and replicate work.

Personalization is an upcoming trend in gamification research, with several researchers proposing that gamified systems should take personal characteristics into account. However, creating good gamified designs is effort intensive as it is and tailoring system interactions to each user will only add to this workload. We propose machine learning algorithm-based personalized content selection to address a part of this problem and present a process for creating personalized designs that allows automating a part of the implementation. The process is based on Deterding's 2015 framework for gameful design, the lens of intrinsic skill atoms, with additional steps for selecting a personalization strategy and algorithm creation. We then demonstrate the process by implementing personalized gamification for a computer-supported collaborative learning environment. For this demonstration, we use the gamification user type hexad for personalization and the heuristics for effective design of gamification for overall design. The result of the applied design process is a context-aware, personalized gamification ruleset for collaborative environments. Lastly, we present a method for translating gamification rulesets to machine-readable classifier algorithm using the CN2 rule inducer.

No abstract

No abstract