The student project LearnLab aims to port a popular open-source programming learning environment called Karel to the browser and optimize the learning curve using usage data. The goal is to measure users’ learning pace and motivation throughout the course. This will allow problematic lessons to be identified and iteratively revised, for example, by making overly difficult lessons easier. Furthermore, the curriculum could later be automatically adjusted for users if their learning pace deviates significantly from the average in certain areas.
The project aims to address the skills shortage in computer science and meet the need for basic programming skills across various disciplines. Learning programming can be challenging for beginners, and the lack of instructors further complicates the learning process. The project offers an innovative way to design learning materials that are evidence-based while adapting them to the individual abilities of users. By adjusting the difficulty level to the learner’s learning pace and prior knowledge, supervision requirements can be reduced and a motivating learning experience can be ensured.
The challenges are both content-related and technical in nature. Meaningful metrics must be defined and their validity validated. Furthermore, the learning application must be adapted to our purposes from a didactic perspective. A significant part of the work therefore involves designing learning content. At the same time, a software application is being developed, which presents many challenges in itself. The learning application itself must function; the data must be sent to a server and then evaluated. Later in the project, the evaluation process may be automated. Initially, the data will be evaluated using frequentist statistics methods, for example, to check for significant deviations from the average learning pace. In the future, machine learning could also be used as a method to develop a more complex recommendation algorithm for suitable curriculum content.