Technology-enhanced Learning Impact Analysis through Categorization and Pattern Recognition by using Clustering Machine Learning Algorithm

Choudhary, Neeraj (2020) Technology-enhanced Learning Impact Analysis through Categorization and Pattern Recognition by using Clustering Machine Learning Algorithm. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (748kB) | Preview
Preview	PDF (Configuration manual) Download (617kB) | Preview

Abstract

STEM related learning and critical thinking is plays a pivot role in a student knowledge development. These skills build the foundation for a student to learn mathematics and programming concepts but in the recent time education institution have observed that student shows less interest in learning math and programming concept with traditional teaching approach which have forced the institution to explore new teaching approach and modernized there education structure. One efficient approach which most of the education institution had accepted is game based learning which allows younger students to learn concepts while playing interesting games or puzzles and based on the student feedback after they have played the game they can evaluate their development on programming skills and education institution can understand the impact of the game on the student learning. This project is to identify the efficient methodology to understand the impact and behaviour pattern of the students by using machine learning clustering algorithm. The main aim of this research to highlight the limitation of the current approach of evaluating the student’s feedback and provide the solution to it with the help of clustering algorithm. The three game (variable, function, loop) data has been imported from the Newton platform and process with the clustering algorithms and evaluated based on how many clusters and efficient grouping of students has been created. The results show the Kmean is more efficient than agglomerative hierarchical clustering in grouping and defining the potential number of the cluster to be used. The insight from this research could be used by National College of Ireland and Dublin City University for future analysis on game-based students’ feedback.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Dan English
Date Deposited:	18 Jan 2021 13:52
Last Modified:	18 Jan 2021 13:52
URI:	https://norma.ncirl.ie/id/eprint/4365

Actions (login required)

View Item