ANALYSIS OF FACULTY PERFORMANCE EVALUATION USING CLASSIFICATION

Abstract

In order to increase the effectiveness of delivery of quality education, it is important to evaluate the performance of two major stack-holders namely students and faculty. Presently, Data Mining has emerged an important area of research in Higher and Technical Education. Data mining techniques are applied in higher education to address and give an insight to educational and administrative problems in HEIs. However, a large portion of the instructive mining research concentrates on modelling and predicting student's performance and a very few research models are available on faculty performance. While evaluating faculty performance, majority of the research used questionnaire as an important tool for collecting feedback from the students. The same method is being used in this research also. In this study, we have applied five Classification Techniques namely Logistic Regression, Decision Tree, Linear SVM, Neural Network and Naive Bayes and used student’s results along with filled questionnaires to predict the performance of faculty. The accuracy, sensitivity and specificity of classification rules were estimated. The findings of the study indicate the effectiveness of classification in evaluation of faculty.