Mining and Modeling Text. Interdisziplinäre Anwendungen, informatorische Weiterentwicklung, rechtliche Perspektiven (MiMoText; PI)

  • This project is concerned with automatically extracting, structuring and interlinking relevant information from primary sources (notably literary texts such as novels) as well as from scholarly publications (such as literary histories), as well as with using the resulting resources for answering research questions in the Humanities.
  • The project is hosted at the Trier Center for Digital Humanities (TCDH) at the University of Trier. It is funded through the “Research Initiative” of the Rhineland-Palatinate government from July 2019 to June 2022.
  • The speaker of the project is Prof. Dr. Christof Schöch, the substitute speaker is Prof. Dr. Claudine Moulin.

COST Action ‘Distant Reading for European Literary History’ (Action chair)

  • This COST Action aims to create a vibrant and diverse network of researchers jointly developing the resources and methods necessary to change the way European literary history is written using computational methods of analysis for large collections of literary texts.
  • This Action is funded by the COST Association from December 2017 to November 2021 (grant identifier CA16204).

Zeta and Company. Measures of distinctiveness for Computational Literary Studies (PI)

  • This project models, implements, evaluates and uses measures and methods to extract distinctive words from two groups of texts.
  • Funded by the DFG (German Research Foundation) from June 2020 to May 2023 as part of the Priority Programme on “Computational Literary Studies”.

Past projects

  • CLiGS – Computational Literary Genre Stylistics (PI, then mentor). This early career researcher group used methods from text and data mining for the analysis of literary texts in French, Spanish and Italian, with a special focus on the relationship between literary style and literary subgenres. Funded by the BMBF (German Federal Ministry for Research and Education) from April 2014 through March 2020 (grant identifiers FKZ 01UG1408 and 01UG1508).
  • Enhanced metadata for improved precision and validation in analytical sylometry (coordinator). The aim of this project is to improve the precision and transparency of stylometric methods of measuring texts similarity, together with partners at Newcastle University (Australia). Jointly funded by the DAAD (German Academic Exchange Service) and UA (Universities Australia) from 2018-2019 (project ID 57388420).
  • DARIAH: Digital Research Infrastructure for the Arts and Humanities (project member, 2011-2014). Infrastructure for Research in Digital Humanities.
  • TEICHI Framework – TEI for Drupal Module (project lead, 2009-2012). Set of Drupal modules for publishing XML-TEI online.
  • Bérardier de Batauts Essai sur le récit (project lead, 2008-2012). Digital Edition project.