Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases

We analyze bias in historical corpora as encoded in diachronic distributional semantic models by focusing on two specific forms of bias, namely a political (i.e., anti-communism) and racist (i.e., antisemitism) one. For this, we use a new corpus of German parliamentary proceedings, Deuparl, spanning...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2021 ACM/IEEE Joint Conference on Digital Libraries (JCDL) s. 51 - 60
Hlavní autoři: Walter, Tobias, Kirschner, Celina, Eger, Steffen, Glavas, Goran, Lauscher, Anne, Ponzetto, Simone Paolo
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2021
Témata:
bias
computational social science
corpus
label propagation
Libraries
polical analysis
Semantics
Size measurement
Social sciences
Statistical analysis
Time measurement
word embeddings
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:We analyze bias in historical corpora as encoded in diachronic distributional semantic models by focusing on two specific forms of bias, namely a political (i.e., anti-communism) and racist (i.e., antisemitism) one. For this, we use a new corpus of German parliamentary proceedings, Deuparl, spanning the period 1867-2020. We complement this analysis of historical biases in diachronic word embeddings with a novel measure of bias on the basis of term co-occurrences and graph-based label propagation. The results of our bias measurements align with commonly perceived historical trends of antisemitic and anticommunist biases in German politics in different time periods, thus indicating the viability of analyzing historical bias trends using semantic spaces induced from historical corpora.
DOI:10.1109/JCDL52503.2021.00017