The comment analysis method consists of a text analysis of open-ended questions. The test can be used as a complement to traditional acceptance testing, interesting when working with product development, since it shows why the consumer has appreciated or not the product. The aim of this study was to evaluate the use of a new methodology (comment analysis) to characterize commercial coffees. Sixty regular coffee consumers took part in the test. Six different coffee brand samples were tested, common (3) and gourmet (3) coffees. Samples were prepared accordingly to the fabricant’s recommendation. Consumers received samples one by one, proved and wrote positive and negative attributes for each one. A principal component analysis (PCA) was done using a correlation matrix with the means of the samples. Hierarchical cluster analysis (HCA) was also performed to find group of samples with similar sensory characteristics, considering Euclidean distances (dissimilary) and Warld's techniques (agglomeration method) and automatic truncation. Results obtained of PCA lead to a good discrimination between the common coffees and gourmet coffees. Many usual attributes were written, and bitter, intense, strong, acidity, full-bodied, flavor and color, for example, were positive characteristics cited about 2 gourmet coffees (Gourmet 1 and 2). Weak flavor/bitterness and light color were listed as negative characteristics for one gourmet coffee (Gourmet 3). The HCA results showed three groups with distinct characteristics of coffee, the first is a common coffee (Common 4), the second is a gourmet (Gourmet 3) and the last is composed of both common and gourmet coffees. This study's conclusion is that Comment Analyses method allows good discrimination of the coffees, but the consumer uses few and same words to define the coffees, probably, because coffee is a complex sample. Moreover, it shows that in consumer’s perception a common coffee can have similar characteristics to gourmet coffee.