Abstract
Objectives: To analyze the sentiment and understand Student’s opinions and satisfaction about university, and the services which introduce by it to reach accuracy in evaluation of the university. Methods: The sentiment of students was analyzed and quantified the satisfaction towards the University by building an algorithm using a set of fuzzy rules. This study proposes an integrated optimization method: applying a set of fuzzy rules with two lexicons (SentiWordNet and AFINN lexicon) besides to other parameter. The lexicons in sentiment anlysis are individual words that can be considered as a unit of opinion information. The proposed fuzzy system integrates Natural Language Processing techniques to analyze and quantify student’s satisfaction towards the University by classify the comments into very positive, positive, very negative, negative, or neutral sentiment classes. Findings: with this approach, the accuracy is more 0.891 compared to Support Vector Machines (SVM), Naïve Bayes, The Fuzzy Inference to analyze the sentiment with their own lexicon Opinion Words Lexicon and classified the sentiment into 2 classpositive, negative and The Fuzzy Inference to analyze the sentiment with only SentiWordNet lexiconin evaluation obtained for University evaluation, the evaluation has been verified by simulation results on MATLAB. Novelty: The novelty of this study lies in the formulation of few fuzzy rules to evaluate the sentiment class of tweets, and the proposed model can be adapted to any lexicon. Keywords: Sentiment analysis; Fuzzy rule; linguistic variables; Students comments analysis
Highlights
Sentiment Analysis is a difficult problem, where the users can freely express their opinions and feelings on different facility and topics[1]
Our work Support Vector Machines (SVM) Naïve Bayes Tthe Fuzzy Inference to analyze the sentiment with their own lexicon Opinion Words Lexicon and classified the sentiment into 2 class- positive, negative The Fuzzy Inference to analyze the sentiment with only SentiWordNet lexicon
This study proposes a fuzzy model for Sentiment Analysis of Student Satisfaction toward the Future University in Yemen
Summary
Sentiment Analysis is a difficult problem, where the users can freely express their opinions and feelings on different facility and topics[1]. There has been a lot of papers have been presented in on sentiment analysis to analyzes people’s opinions, evaluations, and emotions towards entities such as products, services, individuals, and organizations but there was not enough accuracy for the correct assessment. Many papers have used machine learning techniques like Naïve Bayes [2,3,4] and other papers used Support -Vector Machines (SVM) for Sentiment Analysis from tweets [5,6] but the accuracy was not high. A supervised machine learning-based sentiment analysis system for analyzing student reviews about teacher’s performance is proposed[7]. The Support Vector Machine (SVM) is used for classifying reviews into positive, negative, or neutral. In [8] proposed the Fuzzy Inference to analyze the sentiment and classified the sentiment into 2 classes- positive, negative
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
