Tracing Antisemitic Language Through Diachronic Embedding Projections: France 1789-1914
This work addresses the problem of understanding historical antisemitic discourse for historians and social scientists, though it is incremental in applying existing NLP methods to new historical data.
The researchers tracked the evolution of antisemitic language in France from 1789 to 1914 using diachronic word embeddings on a corpus of French texts, revealing a trend of growing antisemitism, particularly from the mid-1880s and peaking during the Dreyfus affair, with specific adverse bias against Judaism compared to other religions.
We investigate some aspects of the history of antisemitism in France, one of the cradles of modern antisemitism, using diachronic word embeddings. We constructed a large corpus of French books and periodicals issues that contain a keyword related to Jews and performed a diachronic word embedding over the 1789-1914 period. We studied the changes over time in the semantic spaces of 4 target words and performed embedding projections over 6 streams of antisemitic discourse. This allowed us to track the evolution of antisemitic bias in the religious, economic, socio-politic, racial, ethic and conspiratorial domains. Projections show a trend of growing antisemitism, especially in the years starting in the mid-80s and culminating in the Dreyfus affair. Our analysis also allows us to highlight the peculiar adverse bias towards Judaism in the broader context of other religions.