Prof. Dr. Christoph Schommer, Prof. Dr. Peter Gilles, Dr. Christoph Purschke (University of Luxembourg)
Modern computers and artificial intelligence have facilitated the collection, retrieval and analysis of large amounts of texts from heterogenous sources. This offers a high potential and many challenges, in particular for applications in the field of History. But working with big texts also raises questions, for example: how can masses of texts be managed, processed, and retrieved efficiently? Furthermore, which algorithms can and should be used to extract valuable information? Is the information gained reliable and durable? This skills training on ‘text mining’ tries to answer these questions. The training was dedicated to PhD candidates with an interest in Text Mining. It is tangent to the field of distant reading, which focuses on the “understanding of literature, not by studying particular texts, but by aggregating and analysing massive amounts of data”, as introduced by Moretti (2013).