Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases
This work addresses the challenge of quantifying historical biases in political texts for historians and computational linguists, though it is incremental as it builds on existing methods for bias analysis.
The researchers tackled the problem of measuring political and racist biases in historical German parliamentary proceedings by analyzing diachronic word embeddings and introducing a novel co-occurrence-based bias measure, finding that their results align with known historical trends of antisemitism and anti-communism.
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 anti-communist biases in German politics in different time periods, thus indicating the viability of analyzing historical bias trends using semantic spaces induced from historical corpora.