Towards improved online course evaluation and feedback using sentimental analysis technique: case study Uganda Martyrs University

Abstract

E-Learning is becoming one of the most effective training approaches. In particular, blended learning is considered a useful methodology for supporting and understanding students and their learning issues. Thanks to e-Learning platforms and their collaborative tools, students can interact with other students and share doubts on certain topics. However, teachers often have less access of students’ problems, emotions and moods they have in classrooms towards the current teaching due to their differences in cognitive capacities, methodology the lecturer employs in among others. A solution for ensuring the privacy of communication among students could be the adoption of a Sentiment Analysis methodology for the detection of the classroom mood during the learning process. This study aimed at improving teaching and learning on the e-learning platform by enhancing the platform with a sentiment analysis system that automatically analyses students’ feedback in real-time and presents the analysis results to the lecturer. The study extracted students’ opinion from teaching evaluation forms of Uganda Martyrs University, preprocessed the data, trained and tested four classifiers (Support Vector Machine (SVM), Naïve Bayes (NB), Decision Tree (DT), and Random Forest (RF)). The test results showed that RF was the most accurate followed by NB and SVM with the same accuracy and the least was DT. The respective accuracies were; 86%, 84%, and 77% respectively. RF was deployed into a web application to enhance the elearning platform. Keywords: E-learning, Sentiment analysis model, Support Vector Machine, Naïve Bayes, Decision Tree, and Random Forest.