PEGASUS aims to efficiently analyze large heterogeneous datasets, link different data types, and place the results into context. To achieve this, it provides a flexible platform that combines semi-automatic analysis, linking, and visualization with state-of-the-art methods in natural language processing and machine learning – while considering legal, ethical, and quality requirements such as traceability, reproducibility, and bias mitigation.

Research Questions

• Develop analytical tools that enable users to derive useful knowledge, insights, and relations from large amounts of heterogeneous data.
• Generate a visual analytics framework that integrates and orchestrates data analysis, visualizations, and interactions to search through and interactively navigate heterogeneous data.

Selected Results

UKON contributes semantic text analysis capabilities, supporting interactive search using domain-specific ontologies to allow for fuzzy text analysis. This allows for an effective knowledge extraction from distributed text data in specialized knowledge management systems, which is visualized using an interactive knowledge graph.