With the rapid development of computer technology, a new educational model, the innovative education learner model, has emerged as a product of the deep integration of technology and education. In this paper, we will begin by organizing the theories and models related to technology acceptance. We will select the UTAUT model, known for its high explanatory power, as the theoretical framework. Subsequently, we will comprehensively analyze the dataset and conduct in-depth habit mining. The effectiveness of applying K-means concepts to address the classification of clusters of learners’ learning habits is confirmed. The feasibility of the LSTM algorithm in predicting learners for exercise responses is also demonstrated. Next, a learning cluster construction method based on intelligent learner clustering is proposed. The methods of MDS+K-means and spectral clustering are selected for clustering. Learning clusters are constructed, and the performance of the two types of algorithms is compared and analyzed. Finally, the enhanced text feature extraction algorithm is utilized to design and implement the corresponding system for the practical application of the innovative educational learner model. The final experiment proves that the text features extracted by the model are effective, with an error rate of only about 2.8%, thus demonstrating that the intelligent educational learning model in this paper is reasonable.
Read full abstract