Sentiment analysis has become a new knowledge resource after the advent of the Internet and World Wide Web. Sentiment analysis is the procedure used to determine the opinion expressed by a person about a particular topic. It additionally manages the expansive measure of the information to process and group the opinion whether the opinion is positive or negative. This paper contributes to the sentiment analysis of the newspaper articles which checks the polarity of the article text either as positive or negative. At first, we pre-process the dataset by removing special characters, numbers and punctuations from the text. By using feature extraction method, adjective is segregated from the pre-processed data set. Later these data are given to classification algorithms namely naïve Bayesian and SVM classifier. © Research India Publications.