Crisis prediction in e-learning through data mining technology: an empirical investigation
Ke Zhu, Jin Zhang
OMPUTER MODELLING & NEW TECHNOLOGIES 2014 18(12C) 23-27
Department of Information Technology, Henan Normal University, East of Construction Road, Xinxiang, China
Crisis warning is a kind of semi-structured or unstructured problems with a lot of uncertainties. In order to examine learners’ actual achievements and timely warning the problems of the students' learning, crisis prediction techniques are imperative as they assist the teachers in monitoring learners’ progress and, determining their development and competencies. Many factors have no historical data and corresponding statistics, therefore crisis prediction is difficult to calculate and evaluate scientifically. There are many conventional methods of analysis has a lot of limitations and the results are not accurate enough. In this paper, a crisis prediction technology method for e-learning courses, based on data mining techniques and detailed student data, is proposed. An empirical field experiment involving 129 university students was conducted. The results were found to be significantly better than those reported in relevant literature.