“CSO Classifier 3.0: A Scalable Unsupervised Method for Classifying Documents in Terms of Research Topics” is a journal paper accepted at the Special Issue of “TPDL 2019 & 2020” at Scientometrics. Angelo Salatino, Francesco Osborne, Enrico Motta Abstract Classifying scientific articles, patents, and other documents according to the relevant research topics is an important task, […]
Being able to characterise research papers according to their topics enables a multitude of high-level applications such as i) categorise proceedings in digital libraries, ii) semantically enhance the metadata of scientific publications, iii) generate recommendations, iv) produce smart analytics, v) detect research trends, and others.
In our recent work, we designed and developed an unsupervised approach to automatically classify research papers according to an ontology of research areas in the field of Computer Science. This approach uses well-known technologies from the field of Natural Language Processing which makes it easily generalisable. In this article, we will show how we can customise the CSO Classifier and apply it to other fields of Science.
Classifying research papers according to their research topics is an important task to improve their retrievability, assist the creation of smart analytics, and support a variety of approaches for analysing and making sense of the research environment. In this paper, we present the CSO Classifier, a new 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. The approach was evaluated on a gold standard of manually annotated articles yielding a significant improvement over alternative methods.