Effects of using wordnet and spelling checker on classification methods in sentiment analysis for datasets using Bahasa

<span>Sentiment analysis was a system for recognizing and extracting opinions in documents. There were two weaknesses sentiment analysis. The first weakness preprocessing can’t recognize slang words so that important should have been recognized became unrecognizable. Second the feature extraction process only based on form of word but similar word. In this paper, we proposed spelling checker wordnet to fix these weaknesses. We also used k-nearest neighbor (KNN), Naïve Bayes, decision tree as methods check classify text. purpose research know effects Wordnet checkers second improve data processing existing dataset list tweets Bahasa. results showed make decrease valued false positives, negatives, true negatives calculation confusion matrix. It can increase accuracy K-NN from 43% 72%, Bayes 41% 71% 47% 75%.</span>