InsightsNet

Current theories and methods of digital humanities, information technology, and linguistics will be combined to an interdisciplinary approach for the construction, annotation and analysis of data sources. In order to test the developed concepts, different data resources, for example Wikipedia and scientific publication databases, are used.

A corpus from two subject areas – climate change discourse and artificial intelligence – will be processed and automatically and manually annotated. The annotations will be used for the linguistic analysis of multimodal corpora and their semantic networking. This should expand the accessibility of text and data corpora for answering complex questions in the respective application contexts.

The developed data and analysis scenarios will be tested and improved in specialist workshops for experts and in workshops for researchers and the interested public.