关键词: 在线协作学习, 学习者特征, 小组划分, 模糊C均值

Abstract: This paper proposes an online learning hybrid grouping algorithm based on fuzzy C-means algorithm  according to learners model with multidimensional features. Firstly, learners multidimensional features components are extracted. Then, based on the homogeneity clustering theory, the fuzzy C-means algorithm is used to cluster the learners according to their learning styles, knowledge levels, learning objectives and interests. At last, based on the heterogeneity clustering theory, learners are grouped according to their activeness and gender. The proposed algorithm not only ensures that learners with similar learning styles, knowledge levels, learning objectives and interests are grouped into the same ones but also takes into account the effects of activeness and gender differences in learning, which makes group division is more reasonable. Experiments show that the proposed algorithm is superior to the traditional grouping methods, the learner’s learning effectiveness and learning satisfaction have been greatly improved.

Key words: online collaborative learning, learners&rsquo, characteristics, group division, Fuzzy C-Means algorithm（FCM）