Aspects Based Opinion Mining for Teacher and Course Evaluation

Abstract

Teacher and course evaluation by students at the end of each term is an important task in almost every academic institution world wide. It helps in assessing faculty performance and suitability of the course in any academic program. The data collected from evaluation comprises of two parts|Likert Scale and open-ended feedback. Computationally, the Likert Scale form can be handled easily as it is numerical in nature but to handle open-ended feedback is a challenging task. Presently, in most of the organizations, it is processed manually, which is error-prone, tedious and full of human biases. To solve this problem, this paper proposes a two-step strategy based on Machine Learning and Natural Language Processing (NLP) techniques. The first step is to extract overall topic of the feedback text using supervised machine learning followed by exploitation of NLP rules to find out specific aspect about which the feedback is given along with orientation of the opinion either positive, negative or neutral. Using, this two-step strategy combining with NLP, machine learning techniques and data from past seven years of real feedback at a public sector university in Pakistan, we are able to achieve a recall and precision of 83.89% and 84% on topic identification i.e. to classify a feedback in teacher and course category. The system is able to extract different aspects of teacher and course with a precision of 83% and recall of 80%, whereas overall sentiment classification accuracy is 90%.