Pedagogue Performance Assessment (PPA) using Data mining Techniques

Abstract

Educational Data Mining (EDM) is a developing domain that exploring pedagogical data by applying different machine learning techniques. It can be considered as a research field which provides intrinsic knowledge of teaching and learning process for effective education. The main objective of any educational institution is to provide quality education to their students. One way to achieve highest level of quality in higher education system is by discovering knowledge that predicts pedagogues performance. This paper presents an efficient system model for evaluation and prediction of pedagogue performance in higher institutions of learning using data mining technologies. To achieve the objectives of this work, three classification algorithms like decision tree algorithms(C4.5), support vector machines (SMO) and artificial neural networks (MLP) are chosen to build classifier models on a dataset. The classifier system was tested successfully using case study data from St. Joseph college of Engineering and Technology, Palai. The data consists of the feedbacks that got from the students. The aim of this work is to demonstrate the capability of EDM in illuminating the criteria of fruitful instructor performance as perceived by the students. The result shows the accuracy of classifier models that predicts the performance of pedagogues. Decision tree J48 have higher accuracy of 94.37% than SMO and MLP.