Supervised learning learns from examples paired with known categories or target outputs, then predicts the category of a new object. section 11.1
An authorship-identification task follows this pattern:
- Collect training data: book texts paired with their authors. section 11.1
- Calculate features such as average word length, average words per sentence, and sentence complexity. section 11.1 section 11.8
- Use the learned relationship between features and authors to predict the author of a book with an unknown author. section 11.1
Authorship identification
Each known book becomes an object with an author label and a signature of writing features. A mystery book supplies new features for an author prediction. section 11.8
