Chapter Semantic analysis of web archive historical data: 1983 “Marche pour l’égalité et contre le racisme”

Abstract

Based on a corpus composed by data obtained from the web archive of the French National Audiovisual Institute, including web pages referencing the history of the 1983 March for Equality and Against Racism, we explored how the memory of a historical event is built through the recounting of web media and the possibilities afforded by computational text analysis methods for the study of large corpuses of historical data from the archived web. This chapter presents the methodology and results of Davide Rendina's master's thesis in computer sciences under the supervision of Sophie Gebeil, Mathieu Génois, and Patrice Bellot. The objective is to demonstrate how historians can utilize archived HTML pages to study the media coverage of historical subjects on the web.