NODES2022 - Data Management with Knowledge Graphs Bringing Archives to Life

NODES2022 - Data Management with Knowledge Graphs Bringing Archives to Life

Vlasta Kůs is Lead Data Scientist at GraphAware and presented at NODES2022. Public archives contain incredible amount of knowledge. In this session, we’ll cover a real use case of building a knowledge graph for the archive of a major foundation to help empower researchers (or business analysts) to access previously unavailable levels of insights. This archive, going up to a century back, contains detailed information about funded projects and conversations preceding them, budgets, research endeavors, and outcomes, as well as priceless knowledge about influence networks of foundation representatives, researchers, and students. A particular challenge was that the same events were described in multiple sources. The only way to leverage all of this knowledge was through the use of advanced analytics and machine learning. We will explore the technologies (including OCR, NLP, and graph data science) and complex pipelines employed to create this major knowledge graph.