In the DFG-funded project "Computational Approaches to Narrative Space in 19th and 20th Century Novels" (CANSpiN), approaches to computer-assisted recognition of narrative space using machine learning methods are being developed and tested on German- and Spanish-language novel corpora in order to answer questions about the relationship between mentions of space and identity constructions. The interdisciplinary project is led by the Junior Professorship for Digital Humanities, the Uwe Johnson Professorship for 20th Century Modern German Literature, and the Associate Professorship for Mathematical Optimization.

Literary theory offers a sophisticated set of tools for conceptualizing and describing narrative space. However, in order to use the existing concepts in computational analyses, they need to be formalized and mapped to features that can be captured on the linguistic surface of the texts. For Distant Reading approaches, it is necessary to develop algorithms that allow automatic annotation of the features. This is the goal of the project in methodological terms.

From a literary-historical perspective, the project will examine how the representation of space in the novels is related to issues of national, regional, and other spatial identities. The corpus-based studies will address existing literary-historical questions about the role of novels in the process of nation-building in the 19th century and their function in the formation of two German identities in 20th-century postwar literature using new, computer-assisted methods and on a broader empirical basis than before.

CANSpiN is part of the DFG priority program "Computational Literary Studies" (SPP 2207).

Project duration: 1.4.2023 - 31.3.2026