This study focuses on sentiment analysis of public opinions regarding the 2024 Indonesian Presidential Election on Twitter. The research employs the Support Vector Machine (SVM) algorithm with Word2Vec feature extraction to analyze the sentiment data. The dataset consists of 14,318 tweets in Indonesian, categorized into positive and negative sentiments. The SVM algorithm, known for its high accuracy, is chosen for its ability to handle extensive sentiment data efficiently and accurately. Word2Vec is selected for its capability to represent contextual similarities between words, enhancing text classification. The study compares four data split ratios (60:40, 70:30, 80:20, and 90:10) to determine the optimal configuration for the model. The results indicate that the 80:20 split ratio yields the best performance, with a precision score of 88.94%, recall of 93.08%, F1-score of 90.43%, and accuracy of 90.75%. This performance surpasses previous research using the SVM method, which achieved an accuracy of 82.3%. The sentiment analysis reveals varying levels of public support for the three candidates: Anies Baswedan, Prabowo Subianto, and Ganjar Pranowo. Anies Baswedan received 23% positive and 67% negative sentiment, Prabowo Subianto received 41% positive and 59% negative sentiment, and Ganjar Pranowo received 36% positive and 64% negative sentiment. The study concludes that the SVM algorithm with Word2Vec feature extraction effectively captures public sentiment and preferences, providing valuable insights for understanding public opinion on the 2024 Indonesian Presidential Election.This study focuses on sentiment analysis of public opinions regarding the 2024 Indonesian Presidential Election on Twitter. The research employs the Support Vector Machine (SVM) algorithm with Word2Vec feature extraction to analyze the sentiment data. The dataset consists of 14,318 tweets in Indonesian, categorized into positive and negative sentiments. The SVM algorithm, known for its high accuracy, is chosen for its ability to handle extensive sentiment data efficiently and accurately. Word2Vec is selected for its capability to represent contextual similarities between words, enhancing text classification. The study compares four data split ratios (60:40, 70:30, 80:20, and 90:10) to determine the optimal configuration for the model. The results indicate that the 80:20 split ratio yields the best performance, with a precision score of 88.94%, recall of 93.08%, F1-score of 90.43%, and accuracy of 90.75%. This performance surpasses previous research using the SVM method, which achieved an accuracy of 82.3%. The sentiment analysis reveals varying levels of public support for the three candidates: Anies Baswedan, Prabowo Subianto, and Ganjar Pranowo. Anies Baswedan received 23% positive and 67% negative sentiment, Prabowo Subianto received 41% positive and 59% negative sentiment, and Ganjar Pranowo received 36% positive and 64% negative sentiment. The study concludes that the SVM algorithm with Word2Vec feature extraction effectively captures public sentiment and preferences, providing valuable insights for understanding public opinion on the 2024 Indonesian Presidential Election.