As part of the special “transverse program” of PSL, the DHAI group organizes with the help of PSL a special 1 week course on the topic of “Digital Humanities Meet Artificial Intelligence”. This course is open in priority to Master 2 students of PSL. It is also open to other students (Master and PhD) and researchers, subject to availability.
This intensive training will cover theoretical and numerical topics, and applications at the intersection between these two fields. The structure of the course will be quite innovative, since it will interplay theoretical topics and practical sessions with computer labs and group projects.
Important: Master students should check with their master’s administration if this course can be used to validate one of their master course.
Dates: 21-25 November 2022.
Location: PariSanté Campus (10 rue d’Oradour-sur-Glane à Issy-les-Moulineaux, 92130)
Pre-register via this Google Form (priority will go to PSL Master 2 students).
This week-long course will be split into three types of classes: theory, practice and project. During the project session, students will work in small groups toward a case study of practical importance. The final examination of the course will be a short presentation of the projects.
Lecture Topics will include:
The practical sessions will feature:
List of Projects:
Project 1: Computational analysis of George Viau’s collection (Léa Saint-Raymond with Quentin Bernet)
Between the beginning of the 20th century and his death, the dental surgeon George Viau (1855-1939) built up an exceptional collection, both in terms of size - some 1,200 artworks - and quality, bringing together the greatest Impressionist and Post-Impressionist names such as Monet, Renoir, Sisley, Pissarro, Degas, Morisot, Toulouse-Lautrec, Cézanne, Van Gogh, Denis, Vuillard and many others. Its after-death sale in 1942 produced the largest turnover in WW2 France. Based on an existing database, created within the framework of the Digital Viau project, this course introduces students to computational analysis. The aim is to reconstruct in detail - and visualize - the complex trajectory of George Viau’s collection, from the acquisition of the paintings, sculptures, drawings and engravings, to their successive dispersals in Parisian public auctions, as well as the networks of buyers and the spatial logics of this corpus. These visualizations will be integrated into the website of the Digital Viau project, and the students will be considered, and cited, as full collaborators in the project.
Project 2: Exploring political debates on Twitter through interactive networks (Armin Pournaki)
In this project, we will learn how to collect, analyze and interpret digital trace data from the social media platform Twitter. We will explore controversial topics through interactive networks, which give a structural overview of the debate’s opinion clusters and their main actors. The textual content shared by these clusters will be analyzed using natural language processing (NLP) methods that you get to know in the theoretical course. Combining the network and NLP analysis with a close-reading of the tweets will allow us to generate hypotheses about the underlying mechanisms of opinion dynamics on online social media.
Project 3: Analysing medieval astronomical diagrams (Tristan Dot & Ségolène Albouy)
This project will be focused on the automatic extraction and analysis of diagrams from astronomical manuscripts. After a first segmentation step (thanks to a convolutional neural network), we will use deep features in order to discover similar diagrams in our digitized corpus. We will explore how to cluster diagrams according to content and shape, without considering “style,” in order to produce the first AI-assisted critical edition of medieval astronomical diagrams.
Project 4: A Computational Literary History of Gender (Jean Barré)
This project proposes an overview of the methods used in the computational literary studies. We will apply Text Mining, NLP & Machine Learning techniques to model concepts in large literary corpora. We will focus on the notion of gender and try to evaluate the strength of gender stereotypes over literary history. We will pass through the process used in the field, from meta-data collection, data annotation, to NLP techniques implementation, predictive modelling and interpretative analysis of our results. Several tasks will be in work, with gender stereotypes detection, character gender prediction, author gender prediction and gendered character screentime evaluation.
Indicative bibliography :
Monday, November 21
Tuesday, November 22
Wednesday, November 23
Thursday, November 24
Friday, November 25