2020/03/24 by David W. Schindler, Schindler, David, Benjamin Zapilko +3
Computer Science · Decision Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Open Source Software Innovations #Scientific Computing and Data Management #Software Engineering Research
paper · pdf · doi:10.48550/arxiv.2003.10715
openalex publication_date 2020/03/24 · openalex created_date 2022/09/21 · openalex updated_date 2026/07/28
Knowledge about the software used in scientific investigations is necessary\nfor different reasons, including provenance of the results, measuring software\nimpact to attribute developers, and bibliometric software citation analysis in\ngeneral. Additionally, providing information about whether and how the software\nand the source code are available allows an assessment about the state and role\nof open source software in science in general. While such analyses can be done\nmanually, large scale analyses require the application of automated methods of\ninformation extraction and linking. In this paper, we present SoftwareKG - a\nknowledge graph that contains information about software mentions from more\nthan 51,000 scientific articles from the social sciences. A silver standard\ncorpus, created by a distant and weak supervision approach, and a gold standard\ncorpus, created by manual annotation, were used to train an LSTM based neural\nnetwork to identify software mentions in scientific articles. The model\nachieves a recognition rate of .82 F-score in exact matches. As a result, we\nidentified more than 133,000 software mentions. For entity disambiguation, we\nused the public domain knowledge base DBpedia. Furthermore, we linked the\nentities of the knowledge graph to other knowledge bases such as the Microsoft\nAcademic Knowledge Graph, the Software Ontology, and Wikidata. Finally, we\nillustrate, how SoftwareKG can be used to assess the role of software in the\nsocial sciences.\n