Visual Analytics for Faculty Teaching Practice and Performance using Educational Mining Techniques

Over the years, in making successful careers, higher education has gained
prominence over the graduate students. Faculty teaching practice and performance
are thus given the utmost importance in developing students’ quality for
performance in academics. The performance of the faculty plays an important role
in academic institutions. Evaluating the faculty members' performance helps to
gather critical information and discover new ways of improving them. In this
paper, the proposed system can be used as a comprehensive system for evaluating,
reporting and analyzing data with a promising audience by utilizing the visual
analytics platform in using the educational mining techniques. Based on different
parameters, the faculty teaching practice and performance are evaluated and
projected by building models. The sample data is collected, preprocessed, and
model learning is done using Decision Tree, Support Vector Machine (SVM) and
Artificial Neural Network (ANN) in this evaluation. Besides, an analysis of the
variable importance for each classifier model is done to see which questions appear
in determining the success of faculty members' performance. The idea of this paper
is to indicate the effectiveness of Visual Analytics for Faculty Teaching Practice
and Performance using Educational Mining Techniques on Student's Self-Reflection Tool (SSRT) survey.