The chapter discusses the automated categorization of texts into predefined categories, a task that has gained significant attention due to the increasing availability of digital documents and the need for efficient organization. The dominant approach in the research community is based on machine learning techniques, which automatically build classifiers by learning from preclassified documents. This method offers advantages over knowledge engineering, including better effectiveness, reduced reliance on expert manpower, and ease of portability to different domains. The chapter covers three main aspects: document representation, classifier construction, and classifier evaluation. It also explores various applications of text categorization, such as automatic indexing, document organization, text filtering, word sense disambiguation, and hierarchical categorization of web pages. The chapter highlights the shift from knowledge engineering to machine learning in the late '90s and the benefits of the latter approach, including the ability to handle new categories and domains without manual intervention. Additionally, it discusses the importance of training sets, test sets, and validation sets in evaluating classifier effectiveness and the role of information retrieval techniques in text categorization.The chapter discusses the automated categorization of texts into predefined categories, a task that has gained significant attention due to the increasing availability of digital documents and the need for efficient organization. The dominant approach in the research community is based on machine learning techniques, which automatically build classifiers by learning from preclassified documents. This method offers advantages over knowledge engineering, including better effectiveness, reduced reliance on expert manpower, and ease of portability to different domains. The chapter covers three main aspects: document representation, classifier construction, and classifier evaluation. It also explores various applications of text categorization, such as automatic indexing, document organization, text filtering, word sense disambiguation, and hierarchical categorization of web pages. The chapter highlights the shift from knowledge engineering to machine learning in the late '90s and the benefits of the latter approach, including the ability to handle new categories and domains without manual intervention. Additionally, it discusses the importance of training sets, test sets, and validation sets in evaluating classifier effectiveness and the role of information retrieval techniques in text categorization.