Artificial intelligence, machine learning and bibliographic control : DDC Short Numbers : Towards machine-based classifying

Digital publications now account for the majority of new accessions at the German National Library each year. Due to this growing number, it has become quite challenging to collect and catalogue these items properly. At the same time, these changes allow for new ways, in which it can use the collections. For a number of years, the DNB has been addressing the question of how subject cataloguing processes can be automated so that bibliographic records can be enriched with metadata as comprehensively and uniformly as possible. In the course of introducing automated subject cataloguing procedures, work is also being done on the automated assignment of Dewey Decimal Classification numbers. For this purpose, a set of abridged DDC numbers based on is being developed.

The article sheds light on how artificial intelligence is used in this process. Furthermore, the challenges posed by the development of DDC short numbers and machine-based classification for different scientific subjects will be addressed. Also, it discusses how the DNB deals with the issues of data provenance, data delivery and quality management. [Publisher's text].