Massive open online course (MOOC) quitting prediction algorithm based on semi-supervised learning

Abstract

The invention relates to a massive open online course (MOOC) quitting prediction algorithm based on semi-supervised learning. Firstly, learning log files of users are acquired from an MOOC website, one part of the acquired users forms a test sample set, and the other part forms a training sample set; secondly, according to the learning log files of the users, behavior features of all samples in the training sample set are counted to obtain n behavior features which most express common features of all samples in the training sample set; thirdly, according to the n behavior features, a semi-supervised learning method is adopted to acquire R classifiers; fourthly, the test sample set is used for testing tagging accuracy of the R classifiers, and the classifier with the highest tagging accuracy is selected; and finally, behavior features of any unmarked user are inputted to the above classifier, and the user is marked. The algorithm of the invention only needs few marking samples, a large amount of manpower and material resources cost for tagging the samples can be reduced, the prediction cost is saved, and the prediction accuracy is also improved.

Description

technical field [0001] The invention relates to computer and information technology, in particular to a large-scale network open course withdrawal prediction algorithm based on semi-supervised learning. Background technique [0002] The maturity of technologies such as Web2.0 and cloud computing has provided new opportunities for education informatization. Large-scale online open courses (MOOC, also known as MOOCs) are the product of Internet application innovation. With the rise of MOOC websites such as edx, coursera, and udacity, and universities such as MIT and Stanford successively offering courses on MOOC platforms, MOOC has received more and more attention and recognition. Relying on the Internet, MOOC provides a large number of students with educational experience such as answering questions, taking exams, watching videos, etc., and enables students to use online forums and other forms of collaborative learning. And the openness of MOOC makes MOOC provide learning op...

AI Technical Summary

Problems solved by technology

This prediction algorithm has the following defects: First, it uses supervised learning to train a model on a large number of labeled sample sets, but the cost of obtaining sample labels is very high. This is mainly reflected in: the first sample has a large number, and the second sample label requires It takes a lot of manpower and time, and marking samples requires professionals; secondly, the feature used by the prediction algorithm is a general feature, which cannot accurately describe the students who dropped out of class, so the prediction accuracy is low

Another prediction calculation method is to calculate the final dropout rate of the course based on the weekly dropout rate. Although this prediction method can predict the dropout rate of a certain course, it cannot be used for specific students or users. Judgment, that is, it is impossible to judge which students or users have withdrawn from the class

Images