Please use this identifier to cite or link to this item:
|Title||Ways to Improving Teacher Performance Using Data Mining (Case Study Training In Ministry Of Education)|
|Title in Arabic||طرق تطوير أداء المدرس باستخدام تنقيب البيانات (دراسة حالة التدريب في وزاة التعليم)|
Measuring the effectiveness of teaching has been applied too heavily in education for many years. It concentrated on evaluating student performance. This study examines the factors associated with the assessment of teachers' performance. Therefore, the main objective of this thesis is to improve the teacher performance, good prediction of training course that will be obtained by teacher in one way to reach the highest level of quality in teacher performance, but there is no certainty if there are an accurate determination of teacher advantage and an increase his efficiency through this session. In this case the real data is collected for teachers from the Ministry of Education and Higher Education in Gaza City. It contains data from the academic qualifications for teachers as well as their experience and courses. The data includes three years and questionnaire contains many questions about the course and length of service in the ministry. We propose a model to evaluate their performance through the use of techniques of data mining like association, classification rules (Decision Tree, Rule Induction, K-NN, Naïve Bayesian (Kernel)) to determine ways that can help them to better serve the educational process and hopefully improve their performance and thus reflect it on the performance of teachers in the classroom. In each tasks, we present the extracted knowledge and describe its importance in teacher performance domain. The results show that, factors such as allowing trainees to participate actively, the clarity of the objectives of the session for the trainees, begins session of knowledge (past experiences) of the trainees, implemented trainees experience they have gained in their classrooms affect in improving professional competence. We have 77.46% accuracy by using Naïve Bayesian (Kernel) and 79.92% by using K-NN.
|Publisher||الجامعة الإسلامية - غزة|
|Files in this item|