Knowledge Technologies for the Social Sciences (KTS)

The team “Information & Data Retrieval” focusses on service and research activities which deal with the efficient search for research data, especially in the social sciences. Users should be supported efficiently and effectively throughout all stages of the information search. To do so, the team conducts research in various IR areas, e.g. interactive information retrieval, entity-based and semantic search or personalization. We concentrate on vertical search in different types of information, such as research data or literature data. The information types are interlinked with each other in order to present the user relations between the data and to enable semantic or entity-related searches across all data (see GESIS-wide search). A current challenge is temporal search in large amounts of web data and digital behavioral data, important forms of data for social science research. The goal of the “Information & Data Retrieval” team is to provide suitable state-of-the-art search technologies for all infrastructures at GESIS and to offer innovative search solutions which base on research in the above mentioned areas.

The team Information Extraction & Linking investigates methods and develops services for the integration and linking of research data and research information. The core task of the team is the establishment of a Knowledge Graph infrastructure using established vocabularies and standards, in order to link GESIS research data with each other and with established vocabularies, knowledge graphs and databases. The team develops innovative methods for extracting and linking research data and information, and conducts research in information extraction and natural language processing (NLP), entity resolution and interlinking, and data fusion. Current challenges arise e.g. by mining research data and linking to/from research data references and other data on the web or linking to large web archives containing e.g. Twitter data. In addition to linking research data and its referencing publications, it also advances the linking and homogenization of established vocabularies and annotation frameworks that support a holistic view of research data along the FAIR principles and facilitate cross-search, e.g. as part of the GESIS-wide search and on the Web.  

The team FAIR Data aims at advancing the usability of research data along the FAIR Principles by research-based consolidation and integration of GESIS’ digital services and by improving the visibility and findability of GESIS data on the Web. To this end, the team conducts research at the intersection of information extraction, knowledge graphs, data integration, and information retrieval, and consistently applies these to the improvement of research data and services. As part of the ongoing development of GESIS' Integrated Information Services, the team continuously collaborates with other teams at KTS and departments at GESIS. In addition, collaboration with national and international research data infrastructure initiatives (especially NFDI) is a central task, ensuring transfer to the community and connectivity to standards and innovations from the community (e.g., on FAIR assessment). The team is involved in three NFDI consortia.