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%.