The Flipped Classroom, Mathematics Achievement, and Attitude Towards Mathematics of Grade 11 Students

Date of Award

8-2021

Document Type

Thesis

Degree Name

Master of Arts in Education, major in Basic Education Teaching (Option 1: Thesis)

First Advisor

Karen Diane S. Natera

Abstract

The study explored the application of Educational Data Mining to enhance guidance and counseling services through the application of the decision tree algorithm to predict academic achievement. A decision tree algorithm was applied to the datasets of one batch of students which include their academic scores from Grades 7 through 10 and cumulatively. Surveys were developed to contextualize and validate the results of the decision tree algorithms and were given to class moderators and guidance counselors. The survey results underwent a thematic analysis where significant themes were identified. The variables which drove the predictions in the decision tree models were compared to the observations of the class moderators and guidance counselors. The results of the study show that Effort Mark, Conduct Mark, Academic Probation Status, and measures of intelligence, cognitive skill, or educational aptitude were relevant for both the decision trees and the relevant themes from class moderators and guidance counselors. The current models produced by the decision trees can predict academic achievement with an accuracy ranging from 52 to 59 percent. Recommendations for enhancing guidance and counseling services include further exploring the variable of Effort and Conduct and its current measures, considering additional measures on stress, anxiety, and depression, considering a more detailed collection of student information, having a centralized database or repository for student data, and exploring the applications of educational data mining to career and counseling services.

Link to Full Text

Share

COinS