Sentiment Analysis or Opinion Mining is a Natural Language Processing (NLP) task which aims to analyse opinions, sentiments and subjectivty present in texts (Pang & Lee, 2008). Despite NLP is not a new research area, only in last decade Sentiment Analysis begins to be actively researched, motivated by the huge quantity of data produced in social media in Web (blogs, microblogs, social networks, forums and reviews of products and services in e-commerce portals).
This Master's thesis aims to research different methods to work out opinion classification in Brazilian Portuguese. This work will use a corpus crawled from the Web - reviews of eletronic products. Our approaches for building classifiers are lexicon-based and machine learning. All the classifiers will be evaluated according to the state-of-art.
Pang, Bo, and Lillian Lee. "Opinion mining and sentiment analysis." Foundations and trends in information retrieval 2.1-2 (2008): 1-135.