Automated text categorization of bibliographic records

This article describes a set of technologies studied within the LIVA (Library Information Visualization and Analysis) project, with the aim to improve access to library data by automated means. In today’s society with its rapid growth of digital information there is an increasing demand for information systems to aid the users in selecting the most relevant information and provide it with a visual structure to make it more perspicuous. In the LIVA project research isconducted to investigate how existing library data can be utilized more effectively by applying machine learning to automatically identify and present categories of information to the user.