K-Nearest Neighbors Algorithm to Student Opinion of the Online Learning Method at Wira Wacana Sumba Christian University

The education sector is one of the areas that has felt major impact Covid-19 pandemic. arises teaching and learning process must be carried out from home using online method. This method raises a variety responses students. what makes researchers analyze these views, both in form positive opinions or negative opinions. analysis by applying sentiment opinion mining comment on Facebook, text processed preprocessing method, labeled it to negative. Based available data, classification K-Nearest Neighbors algorithm. Rapid Miner used experiment data with KNN algorithm order find value accuracy, precision recall. From results research, was obtained 87.00% for accuracy 0.916 AUC value. values ​​are high enough student against this pandemic so research classified as Excellent Classification.