No abstract

No abstract

Learning performance prediction can help teachers find students who tend to fail as early as possible so as to give them timely help, which is of great significance for online education. With the availability of online data and the continuous de-velopment of machine learning technology, learning performance prediction in large-scale online education is gaining new momentum. In order to understand the performance of different machine learning algorithms in predicting multi-category learning performance in large-scale online education, this study com-pares five machine learning algorithms including logic regression, decision tree algorithm, naive Bayes, support vector machine and deep neural network. Based on 100000 data records in the edX open dataset, this study models and forecasts students' learning performance with six online learning behaviors as the eigenval-ues. In the process of modeling, missing value estimation and normalization pre-processing are carried out on the original data at first. After that, six datasets of different sizes are divided as input data. Next, the performance of the five algo-rithms is tested on data sets of different sizes. Finally, SFS, SBS and multiple re-gression analysis are used to explore the effect of behavioral feature selection on algorithm performance. The research was validated and evaluated by three met-rics: precision, recall and F1 score. The results show that the F1 score of the deep neural network with multiple regression analysis feature selection achieves 99.25% in the large-scale dataset, outperforming the related other models by 1.25%.

To analyse speech intention based on discussion texts in online collaborative discussions, automatic classification of discussion texts is conducted to assist teachers improve their abilities to diagnose and analyse the discussion process. The current study proposes a deep learning network model that incorporates multi-head attention mechanism with bidirectional long short-term memory (MA-BiLSTM). The proposed algorithm acquires contextual semantic connections from a global perspective and the role of key feature words within sentences from a local perspective to further strengthen the semantic features of the texts. The proposed model was employed to classify 12,000 interactive texts generated during online collaborative discussion activities. Results show that MA-BiLSTM achieved an overall classification accuracy of 83.25%, which is at least 2.83% higher than those of other baseline models. However, the classification of consultative and administrative interactive texts is minimally effective. MA-BiLSTM achieved better than the existing classification methods for interactive text classification.

No abstract