NORMA eResearch @NCI Library

Exploration and Mining of Educational data for Analyzing Student's Engagement

Yadav, Sri Durga Meghana (2017) Exploration and Mining of Educational data for Analyzing Student's Engagement. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview


In the recent years data mining and analytical tools are used to thoroughly observe and find unanticipated relationships with in the data. They are customized into useful, novel ways for the data owners by extracting insights. A lack of appropriate methods, findings for exploring the student-learning data using advanced feature selection methods has paved way for this idea. Events occurring in the most common sources of diverse learning platforms were identified where ever common engagements are observed facilitating Student participation. Completely anonymous data is used for analysis keeping ethical concerns in mind. LIWC is used for breaking down the text into numerical measures, helped to pop out any interesting patterns in the review comments. This research showcases different available advanced feature selection options while trying to exclude predictors with least impact on the dependant variable. Best subsets, Lasso, Ridge and Elastic net were evaluated with lowest MSE of 0.46 achieved for Ridge regression validated by k-fold technique. The data depicting most common student personalities is classified into 3 groups based on discrete learning events. The contribution of this work is an accurate prediction of linear models entities via validating different feature selection techniques. Student personalities were identified based on most common student participation platforms where both numerical and textual measures were considered for analysis.

Item Type: Thesis (Masters)
Subjects: L Education > LB Theory and practice of education > LB2300 Higher Education
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Caoimhe Ní Mhaicín
Date Deposited: 28 Aug 2018 10:16
Last Modified: 28 Aug 2018 10:16

Actions (login required)

View Item View Item