The primary goal of PEGASUS is to support the efficient and effective analysis of large amounts of heterogeneous datasets, integrating the analysis of different data types and put the analysis results into context. This is achieved by providing a flexible and extensible platform for semi-automatic analysis, linking, and visualization of heterogeneous data based on the latest methods of natural language processing and machine learning. Simultaneously, specific requirements like attribution, reproducibility, accountability, and bias-mitigation, as well as legal and ethical aspects are taken into account. The analysis platform enables the separation of relevant from irrelevant information, the extraction and recognition of objects of interest, the detection of cross-matches, and semantic data exploration through cross-data type search queries.
- 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.
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.
Federal Ministry of Education and Research (BMBF, Germany) in the project PEGASUS (project number 13N15268).