Proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change 2019
DOI: 10.18653/v1/w19-4715
|View full text |Cite
|
Sign up to set email alerts
|

Tracing Antisemitic Language Through Diachronic Embedding Projections: France 1789-1914

Abstract: 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 o… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
6
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
2
1

Relationship

1
6

Authors

Journals

citations
Cited by 10 publications
(7 citation statements)
references
References 24 publications
(20 reference statements)
1
6
0
Order By: Relevance
“…Natural Language Processing for the Analysis of Historical Corpora. The studies closest to ours were presented by Garg et al [13] and Tripodi et al [33]. Similar to us, Garg et al quantify bias in historical corpora employing word vector spaces as proxies.…”
Section: Related Worksupporting
confidence: 54%
See 3 more Smart Citations
“…Natural Language Processing for the Analysis of Historical Corpora. The studies closest to ours were presented by Garg et al [13] and Tripodi et al [33]. Similar to us, Garg et al quantify bias in historical corpora employing word vector spaces as proxies.…”
Section: Related Worksupporting
confidence: 54%
“…We observe the differences between Christian and Jewish target sets through seven different views, each of which is defined with one pair of attribute sets (A 1 , A 2 ). Views b-g) correspond to five bias lines identified by [33]: a) Sentiment. We rely on the widely-used attribute set of pleasant (A 1 ) and unpleasant (A 2 ) terms introduced by [5] and translated to German by [21]; b) Religious.…”
Section: A Bias Specificationsmentioning
confidence: 99%
See 2 more Smart Citations
“…We organize our presentation categorizing words by four streams which have often been recognized by historians as constitutive of antisemitic thought in the 19th century: the religious, the economic, the conspiratorial, and the racial streams of antisemitism (Wilson, 1982). We suggest however to describe them, more generally as streams of bias (refining what we did previously in Tripodi et al (2019), as they are not necessarily the result of straightforward antisemitic expressions, but can be associated to discourse going from stereotype (including literary representations considered only today stereotypical or even antisemitic) to prejudice, to outspoken antisemitic offences (including accusations of conspiracy). To clarify this distinction we should first add historical perspective to our analysis.…”
Section: The Dimensions and Evolution Of A Bias: Between Stereotype And Antisemitic Offencementioning
confidence: 79%