Mining posts in social networks have great potential for new applications. However, the huge amount of data produced every day in these networks makes it impractical for people to manually undertake the task. The Sentiment Analysis returns polarity of tweets written in English about a topic of interest. Two main requirements direct the design and the development of the system: (a) good usability and (b) good precision in determining the sentiments. The topic of interest has a clean interface to enter the keywords that describe the topic of interest and to present the results at several levels of detail. To meet the second requirement, the system uses Naïve Bayes classifier to identify the sentiments of tweets, the literature shows that this algorithm combines good classificatory performance and low response time. The systems also present a good result in measuring its precision in identifying the predominant polarity of Tweets and are related to five different topics of interest.

Keywords : Sentiment analysis, opinion mining, Twitter, Naive Bayes classifier.