Knowledge Graph for Reusing Research Knowledge on Related Work in Data Analytics

Advanced Information Systems Engineering Workshops (CAiSE 2024). Lecture Notes in Business Information Processing. Vol.521 2024
Balasuriyage Aritha Dewnith Kumarasinghe, Mārīte Kirikova

Data analytics projects encompass a multitude of facets, including the types of analytics employed, algorithms utilized, and data sources scrutinized. Despite this wealth of information, there remains a challenge in effectively leveraging previous related work for future projects. Traditional approaches often lack mechanisms for preserving and repurposing the knowledge gained from the analysis of related works. In response, this paper introduces a novel method leveraging RDF triples to encapsulate attributes of analytics projects. These RDF triples are then integrated into a web-based knowledge graph, facilitating the exploration of related work within specific data analytics domains. By harnessing this method, researchers and practitioners can identify valuable resources, including data sources, tools, and algorithms, for future endeavors. To demonstrate its efficacy, we apply this method to the domain of real estate analytics, showcasing its potential to enhance project efficiency and innovation.

Keywords
Knowledge Reuse, Analytics, Knowledge Graphs
DOI
10.1007/978-3-031-61003-5_17
Hyperlink
https://link.springer.com/chapter/10.1007/978-3-031-61003-5_17

Kumarasinghe, B., Kirikova, M. Knowledge Graph for Reusing Research Knowledge on Related Work in Data Analytics. In: Advanced Information Systems Engineering Workshops (CAiSE 2024). Lecture Notes in Business Information Processing. Vol.521, Cyprus, Limasol, 3-7 June, 2024. Cham: Springer, 2024, pp.186-199. ISBN 978-3-031-61002-8. e-ISBN 978-3-031-61003-5. ISSN 1865-1348. e-ISSN 1865-1356. Available from: doi:10.1007/978-3-031-61003-5_17

Publication language
English (en)