Article Title
Quality Improvement in Higher Education Through Normalization of Student Feedback Data Using Evolutionary Algorithm
Abstract
Student Feedback is a vital information that helps not only to evaluate the existing academic practices but also to rectify the discrepancies if any, enabling continuous quality improvement. Often the educational institutions make decisions on the teaching and delivery strategies and requirements of the students based on the students’ Feedback. Due to various factors like the composition of the class in terms of student background, personal relationship with the teacher and other factors, the Feedback generally remains so scattered that at times it may not be possible to arrive at a conclusion based on the feedback. Any decision, based on this already obscure feedback, can only be flawed. This underscores the necessity of normalizing the Feedback data so that one can elicit a clear numerical value for each item in questionnaire rather than quantifying the same in terms of number of responses ‘for’ and ‘against’ the item. Employing an artificial intelligence method, this paper aims at developing an efficient scheme for the analysis of students’ Feedback taking into account the above mentioned factors. Because of its ease of use, the proposed feedback evaluation mechanism can be used on monthly basis in a given academic year, thus achieving continuous improvement of quality. It is hoped that this can serve as an effective tool in improving the learning and teaching methods, standards of education and ultimately the quality of higher education.
