In this chapter, we discussed the issues surrounding the classification of text and examined several approaches to perform this process. The classification of text is useful for many activities such as detecting e-mail spamming, determining who the author of a document may be, performing gender identification, and language identification.

We also demonstrated how sentiment analysis is performed. This analysis is concerned with determining whether a piece of text is positive or negative in nature. It is also possible to assess other sentiment attributes.

Most of the approaches we used required us to first create a model based on training data. Normally, this model needs to be validated using a set of test data. Once the model has been created, it is usually easy to use.

In the next chapter, we will investigate the parsing process and how it contributes to extracting relationships from text.