Answers are grounded in this paper and cite their sources.
Research compares support vector machine and long short-term memory algorithms, suggesting SVM may be more effective in predicting student satisfaction.
Education serves as the primary foundation to fulfill life's needs through the acquisition of adequate knowledge. The educational process aims to create high-quality Human Resources (HR), starting from elementary education to higher education. Performance evaluation of lecturers is essential as they play a vital role in daily interactions with students, impacting student satisfaction. This research aims to compare Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) algorithms in predicting student satisfaction with lecturer performance. The variables used include responsiveness, reliability, appearance, and empathy. The study results are expected to provide further insights into the effectiveness of both methods in predicting student satisfaction. The analysis of SVM and LSTM algorithm calculations is based on satisfaction data from students at the Faculty of Science and Technology, Nahdlatul Ulama University Lampung. Data collection involved feedback from 2462 respondents on lecturer performance obtained from the Quality Cluster in the Faculty of Science and Technology (FASTEK), recorded in an Excel format. The accuracy results of the SVM and LSTM algorithms, based on the evaluation of the testing system, show a comparison of accuracy results. SVM algorithm accuracy is 98.78%, while LSTM algorithm accuracy is 98.68%. It is concluded that the SVM algorithm provides satisfactory results in determining the level of student satisfaction.
No takes yet. Share an insight, caveat, or question.
Dwiatmoko et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: