DOIONLINE

DOIONLINE NO - IJACEN-IRAJ-DOIONLINE-15524

Publish In
International Journal of Advance Computational Engineering and Networking (IJACEN)-IJACEN
Journal Home
Volume Issue
Issue
Volume-7, Issue-5  ( May, 2019 )
Paper Title
Using Big Data and Learning Analytics in India Higher Education to Build Organizational and Analytical Framework for Evaluating Student Engagement
Author Name
Chhavi Rana
Affilition
Department of Computer Science Engineering, Institute of Engineering and Technology, MD University, Rohtak, Haryana, India
Pages
25-29
Abstract
Higher Education is at a point of unparalleled ambiguity and transformation with financial changes leading to increased focus on student focused model that emphasize on student engagement that leads them to better performance and employability [5,6,8]. The stakeholder in Indian Higher Education system faces stiff competition from International Universities and other organizations that are offering flexible education online. The use of Big Data analytics in higher education is a relatively new area of practice and research [4, 8]. Learning analytics (LA) is the process of using this data to improve learning and teaching and refers to the measurement, collection, analysis and reporting of data about the progress of learners and the contexts in which learning takes place. In this paper, a comparative study is carried out using the output from projects implementing learning analytics around the world and there is an attempt to outline how it can be used in Indian Higher Education for evaluating student engagement. The paper proposes a GCM based framework that train the classifier using various machine-learning algorithms – Naive Bayes and Maximum Entropy. The framework for quality indicators for learning analytics aims to standardise the evaluation of learning analytics tools and to provide a mean to capture evidence for the impact of learning analytics on educational practices in a standardised manner. The criteria of the framework and its quality indicators are based on the results of a Group Concept Mapping study conducted with experts from the field of learning analytics. Furthermore, we use different feature sets and machine learning classifiers to determine the best combination for sentiment analysis of student engagement with courses and their performance. The results indicate that the proposed approach could utilize underutilized knowledge, such as distant relationship embedded in PPI graph and provide novel insights about student engagement. Keywords - Student Engagement; Critical Thinking; Achievement; Student Learning, Pedagogy, Learning Analytics, Quality Indicators, Group Concept Mapping, Framework
  View Paper