A behavioral sequence analyzing framework for grouping students in an e-learning system

Abstract

Grouping of students benefits the formation of virtual learning communities, and contributes to collaborative learning space and recommendation. However, the existed grouping criteria are mainly limited in the learning portfolios, profiles, and social attributes etc. In this paper, we aim to build a unified framework for grouping students based on the behavioral sequences and further predicting which group a newcomer will be. The sequences are represented as a series of behavioral trajectories. We discuss a shape descriptor to approximately express the geometrical information of trajectories, and then capture the structural, micro, and hybrid similarities. A weighted undirected graph, using the sequence as a node, the relation as an edge, and the similarity as the weight, is constructed, on which we perform an extended spectral clustering algorithm to find fair groups. In the phase of prediction, an indexing and retrieval scheme is proposed to assign a newcomer to the corresponding group. We conduct some preliminary experiments on a real dataset to test the availability of the framework and to determine the parameterized conditions for an optimal grouping. Additionally, we also experiment on the grouping prediction with a synthetic data generator. Our proposed method outperforms the counterparts and makes grouping more meaningful.

Use of Mobile Technologies in Personal Learning Environments of Intercultural Contexts: Individual and Group Tasks

“…For the formation of groups, the mathematics teacher took into account social attributes such as the ethnic-religious affiliation and the cultural origin of the students, which are part of a group training approach focused on the profile of the students [107]. This approach has been used in previous research [140][141][142] and as stated by Xie, Zou, Lee, Wong, Rao and Ho Wang [143], it is important since it can affect the effectiveness or efficiency of the group members' learning.…”

“…The reduced number of participants [106] allowed the teacher to gain an in-depth understanding of the reality of his classroom. He took into account the social attributes [107] related to the cultural origin, and the ethnic and religious affiliation, as well as the convenience of the students in the learning carried out previously [9], to organize the affiliations in the group task carried out in the study.…”

Neural-fuzzy with representative sets for prediction of student performance

“…Recent approaches applied data mining to improve educational prediction [7,44,45,49,50]. Some typical methods such as prediction rules [48], Bayesian classifier [64], decision tree (ID3, C4.5, ID3 and CART, J48, NBtree, Reptree) [3,43,66], clustering (K-Means), classification (K-Nearest Neighbor) [27,42], and neural network [34] were proposed for MIMO SAPP problem. Márquez-Vera et al [35] used different data mining methods for the prediction of student failure.…”

Designing and Applying a Pedagogical Interaction Model in the Smart Cloud Platform

“…The SCP obtains results through the data analysis and presents it on the target user's terminal. The commonly used analytics include basic statistics, cluster analysis, learning sequence analysis, and temporal pattern mining (Xie, Zheng, & Zhang, 2016).…”