S. Lakshmi Prabha1, A.R. Mohamed Shanavas2

1(Department of Computer Science, Seethalakshmi Ramaswami College, Tiruchirappalli, Tamilnadu, India)

2(Department of Computer Science, Jamal Mohamed College, Tiruchirappalli, Tamilnadu, India)

Introduction

Educational Data Mining (EDM) is an interdisciplinary field utilizing methods from machine learning, cognitive science, data mining, statistics, and psychometrics. EDM uses computational approaches to analyze educational data and address questions in educational research.

E-learning resources like learning management systems (LMS), intelligent tutoring systems (ITS), and school databases of student test scores have created large repositories of data. EDM researchers leverage this data to understand student learning and find models to improve performance.

Methods in EDM include prediction, clustering, relationship mining, distillation for human judgment, and discovery with models. Learning curves reflect the relationship between learning and experience over time, helping teachers and researchers identify patterns and classify data features.

Abstract

Educational Data Mining identifies patterns in educational settings to improve teaching and learning. This study examines EDM methods for assessing student ability and performance in an e-learning environment for mathematics education in India. Using Learning Curve – an EDM visualization method, it compares rural and urban students’ progress in mathematics.

Conducted in two schools in Tamil Nadu, India, the experiment analyzed data on knowledge component level, problem-solving time, and error rate. The findings show the effectiveness of Learning Curve visualization in helping teachers assess students’ granular-level performance and aiding students in understanding their skill development.

Keywords:

Educational Data Mining, learning curve, e-learning, student assessment