Nowadays, with the growth of the digital universe, e-commerce and social networks, a great diversity of information, products and services is available on the Web. A recommender system can aid in user decisions like which product to buy, which movie to watch and which hotel to book. Traditional recommender systems focus on user and item data to generate recommendations. However, empirical studies indicate that context-aware approaches can produce more precise recommendations. Context-aware recommender systems are being extensively investigated. However, there is a lack of automatic methods for extracting this contextual information. With the advancement of Web 2.0 and the growing popularity of social networking and e-commerce, users have been increasingly encouraged to write reviews describing their opinions on items. There is a growing effort to incorporate into the recommender systems the important information that can be extracted from reviews. Some context extraction methods that use text mining techniques have been proposed in the literature. In this way, the objective of this work is to explore and evaluate two context extraction methods in the domain of reviews, a method based in named entities and a method based in topic hierarchies. This exploration allows the construction of baselines to be used in works that are under development in the area of context-aware recommender systems.