E lectric motorcycles are currently trending on Twitter as a distinct two-wheeled vehicle from those using fossil fuels. Electric motorcycles rely on batteries that are charged using electricity. However, there are many opinions about electric motorcycles on social media, especially on Twitter. Nonetheless, tweets and comments on Twitter often contain irrelevant words that can influence sentiment analysis. In this study, sentiment analysis was conducted on 8,000 Twitter data using the FastText and TF-IDF methods as word embedding techniques, along with Support Vector Machine (SVM) as the classification technique. The aim of this research is to compare the performance of SVM using different feature extraction techniques, namely FastText and TF-IDF. The results of this study are expected to be beneficial for electric vehicle manufacturers and individuals interested in electric vehicles. In this comparison, the performance of TF-IDF and FastText feature extraction will be evaluated in sentiment classification with SVM. The performance of SVM will be assessed based on accuracy, precision, recall, and F1-score for each feature extraction technique used. The test results show the highest values to be accuracy of 76%, precision of 75%, recall of 74%, and F1-score of 74% with SVM TF-IDF.