Dispositional Learning Analytics Structure Integrated with Recurrent Neural Networks in Predicting Students Performance

Abstract

The ability to predict a student’s performance can be beneficial for actions in modern educational systems. The manipulation of big volume learning data is a critical challenge for the design of personalized curricula and learning experiences. The purpose of this research article is twofold: (i) an integrated framework for Dispositional Learning Analytics (DLA) to trace student disposition data from the learning management system (LMS), directing to spread learning theory by methodically collecting data from digital platforms. (ii) Analyse the student academic data together with disposition data to perform deep learning model such as recurrent neural networks, bidirectional recurrent neural networks, long-term short memory (LSTM) algorithms to the sustenance of the student behaviour prevention at the same time predict academic performance. To associate the (i) and (ii), we have experimented with a particular course on grade prediction. We have applied feature selection algorithm, machine learning, and deep learning models to identify the prediction. The results show positive and move towards the direction into dispositional learning analytics trace data with academic data to predict student performance.