الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 276 |  |  |
| | | from | 276 | | |
Abstract
The collection and analysis of comments is an important topic, as traditional methods are based on analyzing and collecting students’ feedback in the questionnaire. This thesis aims to extract knowledge to support students’ learning processes through understanding student sentiments on utilizing gamification quizzes in learning. This thesis showed that for applying formative assessment in an innovative way, enriching the activities accompanying the educational process in higher education, and applying the fuzzy logic to get more accurate analysis and reflect the true perceived sentiment in the text’s content.
First, we measured student satisfaction with the sentiment class. We observed that there is a direct relationship between the sentiment score of the SWN lexicon and student satisfaction level. if the sentiment score of the SWN lexicon is increasing, then student satisfaction also increases. where the student satisfaction level was 80% in the SFD dataset, while it was 81% in the SSAGS dataset. Furthermore, when using SVM, NB, and DT classifiers, we found that some aspects have high results because students’ opinions are positive and students’ satisfaction level is higher. For example, the accuracy of the extracurricular aspect is equivalent to 89.19% in the NB and DT classifiers. Also, the accuracy of the library facilities aspect is equivalent to 83.78% in the SVM classifier. Moreover, we found that some aspects have high results because students’ opinions are positive and students’ satisfaction level is higher. For example, the accuracy of the motivation aspect is equivalent to 100% in the SVM and DT classifiers. Also, the accuracy of the clarity aspect and the improvement aspect is equivalent to 92.5% in the NB classifier.
Second, the SFD and SSAGS datasets were evaluated, and each database had two different experiments, one using the SWN lexicon and the other using the SVM, NB, and DT classifiers. The results showed high accuracy and high recall. Finally, the results were compared with previous work and concluded that the current results improved in the process of analyzing student opinions to determine the level of student satisfaction.