Machine Learning-Based Evaluation of Information Literacy Enhancement among College Teachers

Abstract

To enhance the information literacy among college teachers, it is necessary to evaluate their existing information awareness, information ethics, information techniques and information competence. Existing studies qualitatively analysed the effective means of enhancing information literacy among college teachers, and the dimensions were too homogeneous. In response, this paper studies the machine learning-based evaluation of college teachers’ information literacy enhancement. Firstly, the paper presents a framework of predictive model on information literacy enhancement evaluation of college teachers, and the influencing factors of college teachers’ information technology usage behaviour (ITUB) from the authors’ viewpoint. Then the paper presents a framework diagram for extracting ITUB features, along with a detailed introduction to specific influencing factors. After that, the paper extracts the potential information in the content of information technology behaviour to be predicted. The content features of ITUB are characterised by two aspects: content similarity and data form features. Next, the paper shows a method for calculating the affective polarity of ITUB. It also constructs a predictive model for enhancing ITUB and shows the objective function of the model. The experimental results verify the validity of the constructed model.