SLOW LEARNER DETECTION SYSTEM USING EDUCATION DATA MINING (SLD-EDM)
Educational Data Mining (EDM) is the application of Data Mining techniques on educational data. The objective of EDM is to analyze such data and to resolve educational research issues. EDM deals with developing new methods to explore the educational data, and using Data Mining methods to better understand student learning environment [1-4]. The EDM process converts raw data coming from educational systems into useful information that could potentially have a great impact on educational research and practice. Educational Data Mining researchers study a variety of areas, including individual learning from educational software, computer supported collaborative learning ,computer-adaptive testing (and testing more broadly), and the factors that are associated with student failure or non-retention in courses[6,8]. Some other key areas include improvement of student models; application of EDM methods has been in discovering or improving models of a domains knowledge structure and studying pedagogical support (both in learning software, and in other domains, such as collaborative learning behaviours). There are increasing research interests in using data mining in education. This new emerging field, called educational data mining, concerns with developing methods that discover knowledge from data originating from educational environments. Educational data mining uses many techniques such as Decision Trees, Neural Networks, Naïve Bayes, K-nearest neighbour and many others. Prediction and analysis of student performance is an important milestone in educational environment. Student’s academic performance is a crucial factor in building their future[4,5]. Academic performance of student is not a result of only one deciding factor besides it heavily hinges on various factors like personal, socio-economic, psychological and other environmental variables. This paper identifies the factors associated with students whose academic performance is not good and to improve the quality of education by identifying slow learners so that teachers can assist them individually to improve their performance. Through this paper, the accuracy of some classification techniques for predicting performance of a student is also investigated. The main objectives of this work are: to generate data source of predictive variables, Data mining methodologies to study student performance at high school level, identification of the slow learners performance, identification of the highly influencing predictive variables on the academic performance of high school students and to find the best classification algorithm.
Table of Contents