Albrecht Fortenbacher

Predicting students' success based on forum activities in MOOCs

Massive Open Online Courses (MOOCs) have the potential to scale university education, allowing for many thousands of students to participate in a single online course. But even successful MOOC platforms like Coursera, edX or Iversity face the problem of very low completion rates. Analyzing learning activities in a MOOC, learning analytics could help to identify necessary interventions. In Iversity MOOCs, a forum is the basic communication platform, both for student-student and student-instructor communication. In this paper, features of successful students are derived from forum activities and combined to a learning profile. From this learning profile, feedback could be generated for students who are classified as ”risk students”. An analytics tool was developed, based on machine learning, which classifies students in Iversity MOOCs, using features like number of answers in a forum or number of up-votes. Thus, features of successful students can be determined, and visualized in an intuitive way.

Cooking with learning analytics recipes

Learning Analytics is a melting pot for a multitude of research fields and origin of many developments about learning and its environment. There is a serious hype over the concepts of learning analytics, however, concrete solutions and applications are comparably scarce. Of course, data rich environments, such as MOOCs, come with statistical analytics dashboards, although the educational value is often limited. Practical solutions for scenarios in data-lean environments or for small-scale organizations are rarely adopted. The LA4S project is dedicated to gather practical solutions, provide a tool box for practitioners, and publish a cook book with concrete learning analytics recipes for everyone.

[LISA] learning analytics for sensor-based adaptive learning

This paper reports on research conducted in a project named LISA which aims at supporting learners through learner-centered learning analytics using physiological sensor data as well as environmental sensors. We present the concept and a prototypical realization of a mobile sensor device used in LISA.

Improving a Mobile Learning Companion for Self-regulated Learning using Sensors.

The ability to efficiently manage learning is linked to positive learning experience and outcome. However, attaining the ability of self-regulating is not a matter of course for students and it requires an external assistance. A learning companion stemming from intelligent tutoring system (ITS) has non-authoritative, co-present effect as a learning support and with available sensor technology, self-regulated learning can be better promoted. Sensor enhanced learning companion can detect learning states, learning behaviours and context and provide valuable feedback to learners to increase their awareness of learning progress and to effectively manage their learning. Considering the mobility, autonomy of learners along together with current trend in open online learning resources and contents, available embedded sensors are suitable for realising the concept of learning companion for self-regulated learning. The paper reviews a self-regulated learning concept, a learning companion pedagogy and proposes sensor technology for self-regulated learning and learning companion design

User-Centric Approach to the Design of a Mobile Learning Companion.

In the LISA project, a mobile device (SmartMonitor) to support learners will be developed. SmartMonitor serves as a learning companion, receiving a learner’s sensor data, connecting to a learning analytics system and interacting with a learner without distracting from learning. This paper is about design considerations and first prototypical work for a SmartMonitor device.