Intelligent diagnostic feedback in virtual learning environment

Guo, Ruisheng (2019) Intelligent diagnostic feedback in virtual learning environment. Doctoral thesis, London Metropolitan University.

[img]
Preview
Text
Guo,Ruisheng_Thesis_Intelligent-Diagnostic-Feedback-in-Virtual-Learning-Environment.pdf - Published Version

Download (8MB) | Preview

Abstract / Description

This research investigates the current key issues in the area of e-learning in higher education and focuses on how to provide automatic, effective and convenient online feedback to students in order to support students’ learning. In recent years, e-learning has becoming increasingly commonplace in higher education. On the other hand, according to the National Student Survey (NSS) reports (2007-2010), in England, about half of students and 35% of students (2011 -2014), and 30% of students (2015-2016) did not agreed with that: 1, feedback on their work has been prompt; 2, feedback on their work has helped them clarify things they did not understand; 3, they have received detailed comments on their work. These reports reveal that the feedback and its related fields are one of the weakest are as in higher education in England.

This research compares and contrasts several methods in order to investigate the effective use of intelligent feedback towards modelling the stages of students’learning. The work explores the potential benefits of integrating an artificial neural network (ANN) into a Virtual Learning Environment (VLE) system as a means of identifying grouping together of students who would benefit from the same feedback. It investigates the relative effectiveness of different types of feedback and how to optimize the feedback to maximize the facilitation of learning. It explores the ability of neural networks and data analysis techniques to model the stages of students’ learning. The research also assesses the difference in the progress of students’ learning with and without using intelligent diagnostic feedback. The E-learning Snap-Drift Neural Network (ESDNN) is evaluated as one of the potential tools for providing diagnostic, and effective feedback. The ESDNN is enhanced following the first trial, and the enhanced ESDNN system is introduced to the MCQs-Online Feedback System (M-OFS). Four hypothesis are formulated as follows: 1, during thetrials, students improved their understanding by reading given feedback; 2, after using M-OFS system, students get a higher mark in a separate paper test than before; 3, the students who used the system gained higher marks in the final examination than those who did not use the system; 4,studentsaresatisfied withthissystem. Severaltrialsare conducted inorderto evaluate theapproach and the system.

The findings are analyzed and lead to the conclusion that under certain conditions online diagnostic feedback is an effective means of enhancing student learning across a wide range of subject.

Item Type: Thesis (Doctoral)
Uncontrolled Keywords: learning behaviour; diagnostic feedback; neural networks; on-line feedback; artificial neural network (ANN); Virtual Learning Environment (VLE); MCQs-Online Feedback System (M-OFS)
Subjects: 000 Computer science, information & general works
300 Social sciences > 370 Education
Department: School of Computing and Digital Media
Depositing User: Mary Burslem
Date Deposited: 21 Oct 2019 15:19
Last Modified: 21 Oct 2019 15:20
URI: http://repository.londonmet.ac.uk/id/eprint/5220

Downloads

Downloads per month over past year



Downloads each year

Actions (login required)

View Item View Item