Computer-Aided Reading Classes for Enhancement of Critical Thinking Skills Using AI Techniques

Abstract

Critical thinking (CT), or the ability to involve in purposeful, self-regulatory judgment, is extensively recognized as a significant skill. Critical thinking is a learned skill that needs instruction and practice. Computer programs are shared and can demonstrate a concept via sound, attractive animation, and demo. It permits learners to progress at their work and pace independently or to problem-solve in a group. Computers deliver instant feedback, allowing students to know whether their response is right or not. Hence, in this paper, a Machine learning Framework (MLF) has been suggested to assess and monitor computer-aided reading classes for improving student critical thinking skills. To understand a text, the student needs to diagnose its words and access its meaning. Multi-task learning (MTL) has been used in the proposed model for topic tagging questions to enhance the documents sample size. To alleviate the influence of inappropriate word segmentation and consecutive mine information of entire sentences, word depictions and bidirectional gated recurrent unit networks are assumed in our method. The experimental outcomes show that the suggested method enhances the student self-assessment, student monitoring and assessing progress, information processing score, reading comprehension score, and critical thinking level compared to other existing models.