Naive Bayes Classifier Based Digital Intelligence Literacy Prediction for Secondary School Teachers

The key to whether artificial intelligence can play a transformative role in the field of education lies in whether it can effectively collaborate with educators and learners. For teachers, effective human-machine collaboration not only requires them to possess digital literacy and artificial intelligence literacy, but also requires them to organically integrate the two to form “digital intelligence literacy”. The prediction analysis is an approach that employs the use of previous data to make predictions about future possibilities, one effective method is to use a Naive Bayes classifier for prediction. In this paper, the Naive Bayes classifier is employed to predict the digital intelligence literacy of secondary school teachers. The methods employed to predict the digital intelligence literacy of teachers comprise three phases: data collection and preprocessing, feature extraction and classification. The proposed and existing algorithm is implemented in Python. The results of the proposed model will be reported for accuracy, precision, recall, F1-score and also generate ROC curves and AUC values to show that the model is well-trained.