SENTIMENT ANALYSIS OF STUDENT SATISFACTION TOWARDS DISTANCE LEARNING USING MACHINE LEARNING METHOD

Abstract

<p>The Covid-19 pandemic forces the entire society<br />to change their way of life. One of them is the process of face-to-<br />face learning changing into distant learning. Various responses<br />arise from students during the implementation of this new<br />system, both positive and negative, indicating the level of student<br />satisfaction. The sentiment analysis of students' comments<br />during distance learning was conducted using machine learning<br />algorithms and tools Rapid miner. Literature study shows that<br />the Naive Bayes, K-NN, and Decision Tree algorithms have very<br />high accuracy, so this research uses those methods to get high-<br />accuracy results. The research shows the following results;<br />Naive Bayes is 93.80% and class precision for pred. Positive<br />93.80% and pred. negative 100.00%. The K-NN algorithm is<br />92.49% and class precision for pred. positive is 92.37%, pred.<br />negative 100%. The Decision Tree method is 90.81% with a<br />standard deviation of (+-) 0.58 and class precision for pred.<br />positive 90.81% and class pred. negative 0.00%.</p>