Nowadays, Internet-based data classification and interpretation applications are very popular. Those applications automatically detect the information in text and classify it in various classes based on the users’ requirements. Those commercial applications require immediate results for satisfying their costumers and succeed competitors. This paper presents a model that detects the polarity of the tweets in a very efficient manner. In the proposed model, Apache Spark supports scalability for large data sets and the supervised learning is ensuring efficiency. The experiment shows that the proposed method’s performance is better than the Naïve Bayes, SVM, etc. © 2019, Institute of Advanced Scientific Research, Inc.. All rights reserved.