The MOOC Learner Project addresses data science and machine learning challenges arising from investigating MOOC learner clickstream, video watching and forum data. One activity investigates software engineering practices that support extending data schemas. We contribute to the MOOCdb schema that organizes MOOC activity data for retrieval based on student, resource usage and activity. Another activity develops software that transforms schematized data into student weekly variables of a higher level abstraction to facilitate machine learning-based modeling.
Open source software is available at the MOOC Learner Curated, MOOC Learner Quantified, MOOC Learner Visualized and MOOC Learner Modeled git repositories.
This project is supported by a HKUST-MIT Research Alliance Consortium grant and the USA National Science Foundation.