Expression of Political Opinions in Press

In this paper, we present an application designed to analyze news articles from Romanian mass media and extract opinions about political entities relevant to the major political stage. The application was created with the desire to study media polarization around important political events, such as legislative or presidential elections. The application uses different crawlers to extract the data from online newspapers and save it in the database. Then, it uses several Machine Learning techniques for identifying and classifying opinions about given entities over a long span of time. Based on this classification, it generates reports and charts that could be use not only to study political polarization, but also to identify partisan media.