Data mining techniques for classifying and predicting Teachers’ performance based on their evaluation reports

Abstract

Teachers’ performance is a key bridge to ensure 5 successful pedagogical and educational objectives. However, the evaluation of 6 teachers’ performance has been used to be a manual and temperamental task 7 for school principals. This traditional context limits the teachers’ engagement 8 to develop his/her performance as well as the principle to predict the strengths 9 and weaknesses attached. Hence, schools’ principals need to use initiative 10 methods to evaluate the teachers’ performance. In this study, a comparative 11 approach was developed to evaluate the teachers’ performance aiming at 12 avoiding the potential biased and temperamental human behaves in the 13 teacher’s evaluation process. It involves different Data Mining 14 (DM) techniques to identify the key patterns that are driving the teachers’ 15 performance evaluation process. Therefore, the proposed approach extracts 16 several potential and influential indicators mined from a paper-based on 17 teachers’ performance reports at the Directorate of Education/ Southern 18 Ghawrs, along with some demographics variables. Several DM algorithms are 19 used to analyze teachers’ performance reports and predict their performance, 20 such as NB Tree, Naïve Bayes, and Conjunctive Rule methods. The 21 experimental results show a significant prediction accuracy improvement by 22 (33%) when applying NB Tree compared to Conjunctive rule, and (12%) when 23 compared to Naïve Bayes techniques respectively. 24