Opinion Mining is an area that has attracted many researchers, which resulted in several works. There are two types of approaches for detecting opinion: Approaches based on the corpus (Corpus-based Approach) and other approaches based on dictionary (Dictionary-based Approach). In this article, the authors will make a comparative study between the two approaches: the Bayesian method of Turney for the first approach; for the second approach, the authors will study the detection of opinion by the SentiWordNet and then the introduction of fuzzy logic is seen in this method. This study aims to study the theoretical and practical limitations of these two approaches.