This research is about sentiment analysis using the Word2vec model. this research was conducted by Fauzi (2019). But in his research the use of the Word2vec model produces an accuracy of 70%, because the data used is small. In little data Word2vec cannot grasp the similarity of meaning well. So that related research was carried out which uses Facebook data and also Wikipedia article data in Indonesian as a Word2vec model. In this study a comparison of average extraction features of Word2vec and Bag of Centroid base Word2vec was done and a combination of the two was then performed using the Support Vector Machine method. The application of Word2vec Average base feature extraction produces an accuracy of 84% and using Bag of Centroid base Word2vec has an accuracy of 81% with the best number of features when 60 features use the Clustering Hierarchy algorithm. While the combination of the two results in an accuracy of 84.5%. Incorporation increases the possibility of accuracy results because the feature information becomes more complete.