Slowly but surely, social media replaced the traditional sources of information: people’s need to be constantly updated changed our behavior from buying a newspaper or watching TV, to using a Facebook or Twitter account to visualize, in a customizable manner, the day’s hottest news, with the bonus of being able to also comment on them. This paper presents a method to identify a tweet’s polarity (negative, positive, neutral) using SentiFrameNet, a naïve Bayes classifier and an off-the-self semantic role labeling API.