The main objective of this second research axis is to articulate two complementary research approaches on data from text and image corpora: local analysis and detailed description of these corpuses (such as critical editions) and the use of digital research tools more oriented towards quantitative analysis and the development of learning methods applicable to larger corpus sets. With this perspective, our team is working on:
- the design and development of digital environments for critical edition of texts corpora, with particular attention to the problem of collaborative work, visualization of data, and to the ability to make these environments scalable;
- the development of analysis tools and new computerized processing tools using techniques, such as data mining and machine learning;
- the integration and the test of these tools in the digital edition environments and platforms used by humanities teams in their projects.
We are also working to extend these objectives to iconographic corpora, a subject that has not yet been addressed very much in the field of digital humanities, but for which computer techniques give hope for the development of tools adapted to the needs of humanities teams working on this type of data.