Since the development of big data methods and their arrival in the social sciences, several very ambitious initiatives have emerged with the aim of changing the way history research is done. However, the deployment of these new approaches comes up against a great deal of reticence on the part of historians, who, faced with the difficulty of interdisciplinary dialogue, are often sceptical about the very aims of a collaboration in which they fear, sometimes rightly so, being dispossessed of material that they feel they no longer control when it is transformed to be integrated into databases.
These transformation procedures as much as those of analysis raise methodological or even deep epistemological doubts, especially since the tools used are often innovative and have therefore not been able to benefit from much feedback.
The objective of this project is to develop large historical databases by applying data mining methods to them, notably around the analysis of networks of relationships.
It will be done while implementing an iterative approach to the exploration process, based on the appropriation by users of the procedures and tools used and the results of the analyses. To this end, emphasis will be placed on the explicability of the algorithms and on the progressive analysis of the data and the human-machine interaction.
Alexis Pister will present her thesis, entitled "Visual Analysis of Historical Social Networks: Traceability, Exploration and Analysis", funded by DataIA's HistorIA project, on Thursday, December 15th at 2pm.