Computer Science Ontology

The Computer Science Ontology (CSO) is an automatically generated taxonomy of research topics in the field of Computer Science.^[1][2] It was produced by the Open University in collaboration with Springer Nature by running an information extraction system over a large corpus of scientific articles.^[3] Several branches were manually improved by domain experts. The current version (CSO 3.2^[4]) includes about 14K research topics and 160K semantic relationships.^[5]

Computer Science Ontology

Developer(s)	The Open University
Stable release	CSO 3.2 / June 2020
Type	Ontology Taxonomy Linked data
License	Creative Commons Attribution 4.0 International License
Website	cso.kmi.open.ac.uk

CSO is available in OWL, Turtle, and N-Triples. It is aligned with several other knowledge graphs, including DBpedia, Wikidata, YAGO, Freebase, and Cyc. New versions of CSO are regularly released on the CSO Portal.^[6]

CSO is mostly used to characterise scientific papers and other documents according to their research areas, in order to enable different kinds of analytics.^[7] The CSO Classifier^[8] is an open-source python tool for automatically annotating documents with CSO.

Applications

• Recommender Systems.^[9]
• Computing the semantic similarity of documents.^[10]
• Extracting metadata from video lecture subtitles.^[11]
• Performing bibliometrics analysis.^[12]

See also

• Ontology (information science)
• Semantic Web
• Knowledge graph
• DBpedia
• YAGO
• Freebase
• Cyc
• ACM Computing Classification System
• Mathematics Subject Classification (MSC)
• Physics and Astronomy Classification Scheme (PACS)
• PhySH (Physics Subject Headings)