Twitter has become a widely used social media. The amount of data held has led to research such as sentiment analysis. Sentiment analysis has a problem when there are sarcasm sentences, the polarity of the sentiment that should be negative, becomes positive sentiment due to the use of sarcasm sentences. The purpose of this study is to compare the performance of three machine learning methods, namely Support Vector Machine, Randome Forest, and K-Nearest Neighbor to detect sarcasm sentences on Twitter social media. These three methods were chosen because they have a good performance in text classification. The dataset used is taken from Indonesian language twitter with crawling technique. From the results of the study, it was found that the Support Vector Machine method had the best performance with a recall value of 0.97, precision 0.98 and f1-score 0.98.
Copyrights © 2022