Classification and Analysis of MOOCs Learner’s State: The Study of Hidden Markov Model

Haijian Chen ; Yonghui Dai ; Heyu Gao ; Dongmei Han ; Shan Li

Computer Science and Information Systems, Tome 16 (2019) no. 3.

Résumé

In MOOCs, learner’s state is a key factor to learning effect. In order to study on learner’s state and its change, the Hidden Markov Model was applied in our study, and some data of learner were analyzed, which includes MOOCs learner’s basic information, learning behavior data, curriculum scores and data of participation in learning activities. The relationship of the learning state, the environment factors and the learner’s individual conditions was found based on the data mining of the above of learning behavior data. Generally, there are three main conclusions in our research. Firstly, learners with different educational background have different learning states when they first learn from MOOCs. Secondly, the environmental factors such as curriculum quality, overall learning status and number of learners will influence the change of learners’ learning status. Thirdly, the learner’s behavioral expression is an observational signal of different learning states, which can be used to detect and manage the learner’s learning states in different periods. From the analysis results of Hidden Markov Model, it is found that learners in different learning states can adopt appropriate methods to improve their learning efficiency. If the learner is in a negative state, the learning efficiency can be improved by improving the learning environment. If the learner is in a positive state, the positive learning status of the surrounding learners can help him or her maintain current state. Our research can help the MOOCs institutions improve the curriculum and provide reference for the development of MOOCs teaching.

Détail

Keywords: Classification and analysis, Hidden Markov model, MOOCs Learner’s state, Learning behavior, Status transition