Article updated the 29 January 2023

PhD. Defense

The thesis, entitled ‘Detection and Tracking of Events in Historical Press Documents’ was defended in La Rochelle the 10th of November 2022.

It has been reviewed by:

  • Cédrick Fairon, Professeur ordinaire (Université Catholique de Louvain, Wallonie, Belgique)
  • Els Lefever, Hoofddocent (Universiteit Gent, Vlaanderen, België)

And examined by:

  • Karell Bertet, Maîtresse de conférences HDR (La Rochelle Université, France)
  • Benoit Favre, Professeur des universités (Aix-Marseille Université, France)
  • Glenn Roe, Professeur des universités (Sorbonne Université, France)

The thesis has been supervised by:

  • Antoine Doucet (directeur), Professeur des universités (La Rochelle Université, France)
  • Cyril Faucher, Maître de conférences (La Rochelle Université, France)
  • Cyrille Suire, Enseignant-chercheur (La Rochelle Université, France)

The 45 minutes presentation is accessible below (in French). In case of any issue, go directly to the Université de La Rochelle website.

I had the pleasure to be invited at the Royal Library Of Belgium in March 2023 to present my research works. The video (in English) is accessible below.


Télécharger la thèse (idhal: tel-03956089) (19 Mo. − Licence CC BY 4.0)

  • Title: ‘Detection and Tracking of Events in Historical Press Documents’.
  • Keywords: Events in natural language processing · Event tracking · Historical press documents.
  • Financing: Ministère de l’enseignement supérieur, de la recherche et de l’innovation (French Ministry of Higher Education, Research and Innovation).

Current campaigns to digitise historical documents from all over the world are opening up new avenues for historians and social science researchers. The understanding of past events is renewed by the analysis of these large volumes of historical data : unravelling the thread of events, tracing false information are, among other things, possibilities offered by the digital sciences.

This thesis focuses on these historical press articles and suggests, through two opposing strategies, two analysis processes that address the problem of tracking events in the press. A simple use case is for instance a digital humanities researcher or an amateur historian who is interested in an event of the past and seeks to discover all the press documents related to it. Manual analysis of articles is not feasible in a limited time. By publishing algorithms, datasets and analyses, this thesis is a first step towards the publication of more sophisticated tools allowing any individual to search old press collections for events, and why not, renew some of our historical knowledge.


Guillaume Bernard. Detection and Tracking of Events in Historical Press Documents
Computer Science [cs]. Université de La Rochelle (ULR), La Rochelle,
2022. Français. ⟨NNT : ⟩. ⟨tel-03956089⟩