CSO Classifier

The CSO Classifier is an unsupervised approach for automatically classifying research papers according to the Computer Science Ontology (CSO), a comprehensive ontology of research areas in the field of Computer Science. The CSO Classifier takes as input the metadata associated with a research paper (title, abstract, keywords) and returns a selection of research concepts drawn from the ontology.

To use the classifier, we wrapped it in a REST API that can be hosted with Docker. metaphactory references the classifier as an Ephedra REST Service and retrieves CSO concepts for a research paper by passing the title, abstract, and keywords. The retrieved concepts are automatically matched with the KMI data, and hence to competencies in the knowledge graph. The authors of the paper can then retrieve suggestions of competencies discovered in the research papers.

To extract the competencies of a research paper, the classifier has to be triggered with the Update Topics button on the page of the document: