This essay has been submitted by a student. This is not an example of the work written by our professional essay writers.
Nowadays; The Internet has become a common medium that improve the education. E-learning is a process in which education is mean digital learning. E-learning mainly focuses on learner-centric training rather than teacher-centric training, which has been in practice in traditional teaching. The amount of data stored in educational database increasing rapidly without any benefit to the management These databases contain hidden information for improvement of students' performance. In our case study, we will use educational data mining to analyze the data available from Data Base course and bring out the hidden knowledge from it, we will apply data mining techniques to discover association, classification, clustering and outlier detection rules. In each of these four tasks, we will extract knowledge that describes students' behavior.
Keywords: E-Learning, Students' Performance, Data Mining,
The Internet has become a pervasive medium that has changed completely the education environment, and the way of knowledge that shared throughout the world. It provides an easy way to search and access to any information that you need. E- Learning has made knowledge accessible to a large number of people. There are increasing research interests in using data mining in education. This new emerging field, called Educational Data Mining, Data mining concepts and techniques can be applied in E-Learning to discover knowledge from data come from educational environments. Data Mining uses many techniques such as NaÃ¯ve Bayes, Neural Networks, Decision Trees, K- Nearest neighbor, and many others, to offer useful knowledge about the learning process for instructors.
Data mining known as Knowledge Discovery in Database, Data mining techniques are used to extract or "mining" knowledge and discover hidden patterns from large volumes of data, this knowledge is helpful in decision making, data mining is actually part of the knowledge discovery process. . Mining online learning events is becoming promising area for research and development, particularly when the business in education is growing impressively. Higher education is become a big business, with growing of IT technology supporting online learning. The world is going fast towards online learning, so we can see a lot of open universities that provide courses online through the Internet. So one can study and take the exam and get certified whenever and wherever he/she wants.
Romero and Ventura , have a survey on educational data mining between 1995 and 2005. They concluded that there is growing interest in data mining and the evaluation of online educational systems, educational data mining a rising and promising area of research. Al-Radaideh et al. , applied the data mining techniques to evaluate student data and study the main attributes that may affect the student performance in courses. The extracted classification rules are based on the decision tree as a classification method. It allows students to predict the final grade in a course under study. Baradwaj and Pal , used the classification task to evaluate student' performance, they used decision tree method for classification. The goal of their study is to extract knowledge that describes students' performance in end semester examination. This study helps earlier in identifying the dropouts and students who need special attention and allow the teacher to provide appropriate advising.
Chandra and Nandhini , applied the association rule on students' failed courses to identify the reason for students' failure patterns courses and suggest relevant causes of the failure to improve the low capacity students' performances. It also reveals some hidden patterns of students failed courses which could serve as base for academic planners in making academic decisions and an aid in the curriculum re-structuring and modification, it will help to improve students' performance and reducing failure rate
Mohamed and Alaa , applied educational data mining to extract useful knowledge from graduate students data to improve graduate students' performance, and overcome the problem of low grads of graduate students.
Students are main assets of educational institutions. The students' performance is an important factor to produce the best quality graduates. Students have to place the greatest effort in their study to obtain a good grade to achieve their academic carrier. Many factors could act as barrier and catalyst to students, these factors will reflect on student to achieve a high grade or low grade.
Islamic Since University of Malaysia (USIM) does not use any knowledge discovery process approach to get knowledge about student' performance, decision making in educational system need to these knowledge:
To overcome the problem of low grades of graduate students.
Identifying the dropouts and students who need special attention and allow the teacher to provide appropriate advising/counseling.
Scope Of Research
In this research we will extract knowledge from graduate student data collected from the college of science and technology-USIM. The data include five years from 2007-2012. We will predict their performance to get helpful knowledge that will improve the graduate quality.
The main objective of this research is using data mining methodologies to study studentsâ€Ÿ performance in e-learning
Discover hidden information of students' performance.
This prediction will help to identify the weak students and help to score better mark and reduce fail ratio.
This study will help to the students and the teachers to improve the performance of the students.
Identify those students which needed special attention.
Provide to the decision maker helpful constructive recommendation to overcome the problem of low grade of graduate students.
Improve students' academic performance.
What is the current level of graduate students at USIM?
Do USIM' decision maker have a good knowledge about students' performance?
Do students need special attention to improve their performance?
The methodology used in this research starts from the problem definition, then data collection and preprocessing, then we come to the data mining methods which are association, classification, clustering, and outlier detection, followed by the evaluation of results and patterns, finally the knowledge representation process.
Understanding the domain and problem definition.
Data collection and preprocessing: the data will collect from Graduate Students data base, and the data will clean and transformed into a mineable format.
Apply data mining techniques: the data mining techniques will apply to discover and summarize knowledge about student performance.
Followed by the evaluation of results and patterns, process.
Finally the knowledge representation.
In this research we will discover hidden information from graduate student data collected from the college of science and technology in USIM. The data include five years from 2007-2012. This data existing and available in the USIM database, particularly we use association rules to discovering, Rule Induction and Decision Tree to predict grade of students. The result will contain helpful knowledge, this knowledge can provide to decision maker to improve the graduate quality.