<![CDATA[As a result of the Covid-19 virus pandemic, Universitas Brawijaya implemented an online learning system. The implementation of online learning at Brawijaya University has generated a lot of positive and negative opinions on Twitter. This study aims to determine the level of tendency of positive opinions and negative opinions through the sentiment classification process, as well as to find out some of the things that are often complained of in the implementation of online learning at Brawijaya University. The sentiment classification process is carried out using the K-Nearest Neighbor method in the Rapid Miner application. The sentiment classification process is carried out through four main stages, namely the data collection stage, the data pre-processing stage and term weighting, the classification stage, and the testing stage. In addition, a separate calculation of the frequency of occurrence of words is also carried out. In the classification, the results showed that 50.8% of sentiments gave negative opinions, while the remaining 49.2% gave positive opinions. In the process of calculating the frequency of occurrence of words, five words were often complained about, namely the word "offline", "lecturer", "assignment", "quota", and "ukt". In the testing process, a variation of the k value is tested and its effects on accuracy, precision, and recall. In testing, the analysis process of test results, cross validation testing, and feedback stages is also carried out. On the test, the best accuracy, precision, and recall values ​​were 80% for k = 7, 81.48% for k = 7, and 88.89% for k = 23.]]>
Copyrights © 2021
