Exploring learning analytics for computing education

Student retention in STEM disciplines is a growing problem. The number of students receiving undergraduate STEM degrees will need to increase by about 34% annually in order to meet projected needs [6]. One way to address this problem is by leveraging the emerging field of learning analytics, a data-driven approach to designing learning interventions based on continuously-updated data on learning processes and outcomes. Through an iterative, user-centered, design approach, we propose to develop a learning dashboard tailored for computing courses. The dashboard will collect, analyze, and present learning process and outcome data to instructors and students, thus providing an empirical basis for automated, teacher-initiated, and learner-initiated interventions to positively influence learning outcomes and retention. Through a series of mixed-method empirical studies, we will determine what data should be made available to instructors, how that data can be best displayed, how effective teaching interventions can be fashioned from the data, and how such interventions affect student grades and persistence in introductory computing science courses.