Generally, broad textual collections are thematically organized in hierarchies of categories: web pages are grouped by topics in web directories, emails are arranged in personal folders, articles in digital libraries are indexed by subjects, etc. Hierarchical text categorization explores automatic techniques to assign textual documents to categories in a hierarchy. This book focuses on two main aspects of hierarchical categorization: classification algorithms and performance evaluation. Two general hierarchical frameworks, global and local top-down, extended for DAG hierarchies,...
Generally, broad textual collections are thematically organized in hierarchies of categories: web pages are grouped by topics in web directories, e...