Automatic action analysis in an interactive learning environment

Martin Mühlenbrock

In: Proceedings of the workshop on Usage Analysis in Learning Systems at the 12th International Conference on Artificial Intelligence in Education AIED-2005. International Conference on Artificial Intelligence in Education (AIED), Amsterdam, Pages 73-80, 2005.


Recently, there is a growing interest in the automatic analysis of learner interaction data with web-based learning environments. The approach presented in this paper aims at helping to establish a basis for the automatic analysis of interaction data by developing a data logging and analysis system based on a standard data base server and standard machine learning techniques. The analysis system has been connected to a web-based interactive learning environment for mathematics teaching, but is designed to allow for interfacing also to other web based learning environments. The system has been tested in a five-month experiment in which four classes of a secondary school participated throughout a complete school term on a weekly basis.


Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence