aiqbench analysis
This study applies BlameBERT, a specialized NLP classifier, to analyze political discourse in the Danish Parliament, demonstrating how machine learning can quantify rhetorical hostility and ideological asymmetry over time. The research highlights that perceived increases in political polarization are driven by specific interactions between government status and right-wing ideology rather than a uniform decline in civility. By combining advanced language models with statistical modeling, the work provides robust evidence on the mechanics of blame attribution in low-resource linguistic contexts.
Blaming Across the Aisle: Political Contrasting and Blame Attribution in the Danish Parliament
arXiv:2609.26346v1 Announce Type: new Abstract: Political discourse is widely perceived to be growing more hostile, yet robust evidence remains scarce. This study examines blame attribution in the Danish Parliament from 1997 to 2026, combining a purpose-built classifier, BlameBERT (F1: 0.80), with multilevel statistical modeling. The classifier is constructed using an annotation-efficient pipeline for blame attribution in low-to-mid resource languages. The results reveal a banana-shaped trajectory, with blame declining until around 2016 before entering a significant and sustained increase in recent years (2019-2026). Government status consistently influenced blame attribution - an effect we term political contrasting - with opposition parties blaming substantially more than governing parties. This effect was moderated by ideology: The blame-dampening effect of governing was less pronounced among right-wing parties, and ideological extremity amplified blame more strongly on the right. In recent years, the interaction between political wing and ideological extremity intensified, suggesting an ideological hardening of the blame rhetoric concentrated on the right of the political spectrum. Taken together, these patterns suggest that the perceived rise in harsh political language reflects not merely a general rhetorical drift, but an ideologically asymmetric hardening of political discourse. A sensitivity analysis showed that the conclusions were robust to varying classification thresholds.
Abstract:Political discourse is widely perceived to be growing more hostile, yet robust evidence remains scarce. This study examines blame attribution in the Danish Parliament from 1997 to 2026, combining a purpose-built classifier, BlameBERT (F1: 0.80), with multilevel statistical modeling. The classifier is constructed using an annotation-efficient pipeline for blame attribution in low-to-mid resource languages. The results reveal a banana-shaped trajectory, with blame declining until around 2016 before entering a significant and sustained increase in recent years (2019-2026). Government status consistently influenced blame attribution - an effect we term political contrasting - with opposition parties blaming substantially more than governing parties. This effect was moderated by ideology: The blame-dampening effect of governing was less pronounced among right-wing parties, and ideological extremity amplified blame more strongly on the right. In recent years, the interaction between political wing and ideological extremity intensified, suggesting an ideological hardening of the blame rhetoric concentrated on the right of the political spectrum. Taken together, these patterns suggest that the perceived rise in harsh political language reflects not merely a general rhetorical drift, but an ideologically asymmetric hardening of political discourse. A sensitivity analysis showed that the conclusions were robust to varying classification thresholds.
8 Pages + appendix (25 total) Main paper 4 figures 2 tables: Appendix 9 figures 10 tables. Model found here: this https URL , dataset here: this https URL. Markus Lundsfryd Jensen and Rune Egeskov Trust have contributed equally. Paper will be submitted through ACL rolling review (ARR), we are aiming for COLING 2027
Computation and Language (cs.CL)
arXiv:2609.26346 [cs.CL]
(or arXiv:2609.26346v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.26346 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 269 words
Related coverage
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · Aug 3, 2026
The current bottleneck is political will, not research
AI Alignment Forum · Jul 11, 2026
[AINews] Gemini 4 Argon: GDM’s answer to Astra/Fable, with 1M output
Latent Space · Oct 1, 2026
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
LessWrong · Sep 21, 2026