Analisis Sentimen Pengguna Twitter terhadap Tren Cryptocurrency di Indonesia dengan Metode Support Vector Machine

Abstract

The rapid growth of cryptocurrency as a digital asset has attracted increasing public attention in Indonesia, influened by the extensive adoption of the internet and social media. Among various social media platforms, Twitter (X) has become one of the primary platforms where users express opinions and engage in discussions about cryptocurrency. The information generated from these interactions can be utilized to identify public sentiment trends. This investigation intends to assess public opinion regarding cryptocurrency trends in Indonesia by applying the Support Vector Machine (SVM) algorithm. The research adopts the Knowledge Discovery in Database (KDD) methodology, which consists of data selection, preprocessing, transformation, data mining, and evaluation stages. Data were collected through a web crawling process using the Tweet Harvest application, resulting in 7,000 Indonesian-language tweets. After duplicate removal and preprocessing, 4,502 tweets were retained as the research dataset. Feature extraction was performed using the Term Frequency–Inverse Document Frequency (TF-IDF) method to convert textual data into numerical representations, while sentiment classification was conducted using a linear-kernel Support Vector Machine. Model performance was evaluated using a Confusion Matrix. The experimental results demonstrated that the proposed model achieved an accuracy of 82.35%, precision of 84%, recall of 83%, and an F1-score of 84%. These findings indicate that the combination of TF-IDF and Support Vector Machine provides effective performance for classifying public sentiment regarding cryptocurrency trends in Indonesia.