The Computer Science Ontology: A Comprehensive Automatically-Generated Taxonomy of Research Areas

Abstract

Ontologies of research areas are important tools for characterizing, exploring, and analyzing the research landscape. Some fields of research are comprehensively described by large-scale taxonomies, e.g., MeSH in Biology and PhySH in Physics. Conversely, current Computer Science taxonomies are coarse-grained and tend to evolve slowly. For instance, the ACM classification scheme contains only about 2K research topics and the last version dates back to 2012. In this paper, we introduce the Computer Science Ontology (CSO), a large-scale, automatically generated ontology of research areas, which includes about 14K topics and 162K semantic relationships. It was created by applying the Klink-2 algorithm on a very large data set of 16M scientific articles. CSO presents two main advantages over the alternatives: i) it includes a very large number of topics that do not appear in other classifications, and ii) it can be updated automatically by running Klink-2 on recent corpora of publications. CSO powers several tools adopted by the editorial team at Springer Nature and has been used to enable a variety of solutions, such as classifying research publications, detecting research communities, and predicting research trends. To facilitate the uptake of CSO, we have also released the CSO Classifier, a tool for automatically classifying research papers, and the CSO Portal, a Web application that enables users to download, explore, and provide granular feedback on CSO. Users can use the portal to navigate and visualize sections of the ontology, rate topics and relationships, and suggest missing ones. The portal will support the publication of and access to regular new releases of CSO, with the aim of providing a comprehensive resource to the various research communities engaged with scholarly data.

Enhancing Knowledge Graph Extraction and Validation From Scholarly Publications Using Bibliographic Metadata

“…The restriction of the set of considered publications according to their research areas as revealed in citation indexes or through the analysis of author keywords allows refining the creation and validation of knowledge graphs by eliminating outputs outside the scope of the developed resource (Salatino et al, 2020). This prevents the overlapping of concepts from different fields when they are represented by the same polysemous term and consequently eliminates noise from the generated database.…”

Integrating Knowledge Graphs for Analysing Academia and Industry Dynamics

“…AIDA was generated using an automatic pipeline that integrates and enriches data from Microsoft Academic Graph, Dimensions, Global Research Identifier Database, DBpedia, CSO [14], and INDUSO. It consists of three steps: i) topics detection, ii) extraction of affiliation types, and iii) industrial sector classification.…”

“…4M articles and 5M patents are also classified according to the type of the author's affiliations (academy, industry, or collaborative) and 66 industrial sectors (e.g., automotive, financial, energy, electronics) obtained from DBpedia. AIDA was generated by integrating several knowledge graphs and bibliographic corpora, including Microsoft Academic Graph (MAG), Dimensions, English DBpedia [8], the Computer Science Ontology (CSO) [14], and the Global Research Identifier Database (GRID) 8 . It can be downloaded for free from the AIDA website 9 under the CC BY 4.0 license.…”

Ontology Extraction and Usage in the Scholarly Knowledge Domain1

“…We also mapped the CSO topics to the Fields of Study (FoS) concepts reseased by Microsoft Academic. More details regarding the alignment between CSO and other knowledge bases are avaliable in Salatino et al [26].…”

“…In this chapter, we present the Computer Science Ontology (CSO) Framework [27,26], which is a conceptual framework for generating a large scale ontology of Computer Science. This solution has been used to support a variety of high-level tasks, such as (i) categorising proceedings in digital libraries, (ii) enhancing semantically the metadata of scientific publications, (iii) generating recommendations, (iv) producing smart analytics, (v) detecting research trends, and others [20,27].…”