Simply stating, text classification is all about putting a piece of text into a set of (mostly predefined) categories. This is one of the most important problems which occurs in many real world applications. For example one example of text classification would be an automated call centre which would like to categorise the complaints automatically into the most appropriate bucket of problems.
Text classification is a sub-problem of a more general problem of classification. In this application, the input is represented with a piece of text (rather than images, sounds, videos etc). The output could be:
- binary (binary classification)
- one category out of k possible categories (multi-class)
- a set of categories out of k possible categories (multi-label).
In text classification, the feature extracted from the text are usually sparse (instead of dense, like in image classification).
