Sentiment analysis is applied over entities (companies, agencies, individuals, products), which are mentioned in the texts with a positive, negative or neutral characterization. Our algorithms are able to identify the different entities mentioned in a text, distinguish the various writings of an entity (e.g. full name of a company or its initials) and emotionally charged words that express a positive or negative opinion to them. Using syntactic analysis we are also able to decide on the emotional power of the text and consequently to aggregate opinions and define the emotional impact of an organization / brand / product.
