The author of this document has limited its availability to on-campus or logged-in CSUSB users only.

Off-campus CSUSB users: To download restricted items, please log in to our proxy server with your MyCoyote username and password.

Date of Award


Document Type

Restricted Project: Campus only access

Degree Name

Master of Science in Computer Science


School of Computer Science and Engineering

First Reader/Committee Chair

Gomez, Ernesto


Sentiment analysis is done to perform text classification on the data given by the students. The proposed system collects the feedback from the students after completion of their respective courses and then determines the nature of the feedback which will help the faculty to get review of the courses and analyze the thoughts of students to improve the course. Before using the proposed system, we validate the application by testing a classified dataset and get the accuracy. We use Naive Bayes classifier to classify the data. The classified dataset is divided into training dataset and testing dataset. These datasets must be processed with set of operations such as tokenization, removing characters, lemmatization and vectorization of the data to make it easier for algorithm to test the dataset. A sentiment analysis model based on the Naive Bayes classifier is trained with training dataset and then we test the testing dataset with the proposed model. The score we got from testing classified dataset determines the validity of our system. Once the proposed system is validated, it will use sentiment analysis to calculate the probability determined by the proposed model and classify the data as either positive review or negative review. This will be useful for professors and faculty to get the review of feedbacks given by students without reading all of them.