Data Preparation Strategy in E-Learning System using Association Rule Algorithm

Abstract

Espejo and César Hervás [2] compared different data mining methods and techniques for classifying students based on their Moodle usage data and the final marks obtained in their respective courses. They have developed a specific mining tool for making the configuration and execution of data mining techniques easier for instructors. The research [3] proposes a framework of a personalized learning recommender system, which aims to help students find learning materials they would need to read. Two related technologies are developed under the framework: one is a multi-attribute evaluation method to justify a student's need, and another is a fuzzy matching method to find suitable learning materials to best meet each student need. The implementation of this proposed personalized learning recommender system can support students online learning more effectively and assist large class online teaching with multi-background students. Seki, K., Tsukahara, W., & Okamoto, T [4] developed an integrated e-Learning environment which integrates learning history and learning content information to control each learner's learning. They have been developing an LMS based on Learning Ecological Model which is a model of Learning Environment focusing on learning content, learning objective, and learning style. By analyzing access log and report submission log, they obtained suggestions for improvement such as restriction of browsing period to make students access constantly, fragmentation of report submission deadline for students not keeping report assignment too. C. Romero, S. Ventura and E. Garcia [5] described the full process for mining e-learning data step by step as well as how to apply the main data mining techniques used, such as statistics, visualization, classification, clustering and association rule mining of Moodle data. Hamalainen, W., Suhonen, J., Sutinen, E., & Toivonen, H designed and implemented Data Mining System (DMS) to analyze the study records of two programming courses in a distance curriculum of Computer Science. Various data mining schemes, including the linear regression and probabilistic models, were applied to describe and predict student performance. The purpose of study [10] was to identify and examine learning processes, based on data extracted from log files, which document the learners' action within an online learning environment. For this purpose, log files of four elementary school students, studied with a science Web-based module, were examined and analyzed. A Learnogram -graphical representation tool that visualizes students' learning process over time -was produced for each student. Based on the log files and the Learnograms, seven learning variables were defined and computed, reflecting the differences between the learning processes. 3. DATA PREPARATION STRATEGY Here in this Course Recommendation System, we have considered the 13 course category which is shown in following table 1. Under each category there will courses. So there are about 82 courses.