Clustering Analysis of Interactive Learning Activities Based on Improved BIRCH Algorithm
This work addresses the need for data-driven education decision-making by improving clustering methods for learning analytics, though it appears incremental in nature.
The paper tackled the problem of analyzing group tendencies in computer-assisted learning by clustering multi-dimensional learning interaction activities, and found that their improved BIRCH algorithm showed obvious advantages in clustering performance with feasible and reliable results.
Group tendency is a research branch of computer assisted learning. The construction of good learning behavior is of great significance to learners' learning process and learning effect, and is the key basis of data-driven education decision-making. Clustering analysis is an effective method for the study of group tendency. Therefore, it is necessary to obtain the online learning behavior big data set of multi period and multi course, and describe the learning behavior as multi-dimensional learning interaction activities. First of all, on the basis of data initialization and standardization, we locate the classification conditions of data, realize the differentiation and integration of learning behavior, and form multiple subsets of data to be clustered; secondly, according to the topological relevance and dependence between learning interaction activities, we design an improved algorithm of BIRCH clustering based on random walking strategy, which realizes the retrieval evaluation and data of key learning interaction activities; Thirdly, through the calculation and comparison of several performance indexes, the improved algorithm has obvious advantages in learning interactive activity clustering, and the clustering process and results are feasible and reliable. The conclusion of this study can be used for reference and can be popularized. It has practical significance for the research of education big data and the practical application of learning analytics.