Academic industries used to collect feedback from the students on the main aspects of course such as preparations, contents, delivery methods, punctual, skills, appreciation, and learning experience. The feedback is collected in terms of both qualitative and quantitative scores. Recent approaches for feedback mining use manual methods and it focus mostly on the quantitative comments. So the evaluation cannot be made through deeper analysis. In this paper, we develop a student feedback mining system (SFMS) which applies text analytics and sentiment analysis approach to provide instructors a quantified and deeper analysis of the qualitative feedback from students that will improve the students learning experience. We have collected feedback from the students and then text processing is done to clean the data. Features or topics are extracted from the pre-processed document. Feedback comments about each topic are collected and made as a cluster. Classify the comments using sentiment classifier and apply the visualization techniques to represent the views of students. This proposed system is an efficient approach for providing qualitative feedback for the instructor that enriches the students learning.