How do medical authorities express their sentiment in Twitter messages?

Opinion mining is a process, used for automatic extraction of knowledge from the opinion of others about some particular topic or problem. Further, opinions are subjective expressions that describe people´s viewpoints, perspectives or feelings about entities, events and theirs properties. Detecting subjective expressions is the task of identifying whether a given text is subjective (i.e. an opinion) or objective (i.e. a reports fact). This task is considered as the first problem and it is very important for opinion mining and sentiment analysis. This research aims to analyze publicized stream of tweets from the Twitter microblogging site. The data stream are preprocessed and classified based on their emotional content as positive, negative and neutral. The data analysis is limited to a particular set of users. Firstly, we collect and process post comments on Twitter. Then the post was analyzed by lexical and syntactic approach. In experiment results, we detects more neutral emotional states than positive or negative (31%). We also applied statistical methods in order to infer if there exist correlation between user reputation and emotional content. The finding suggest that did not exist a strong correlation between user reputation and emotional content. From our observation, user reputation do not follow any emotional rules.