Analysing Calls to Order in German Parliamentary Debates

Nina Smirnova; Daniel Dan; Philipp Mayr

cs.CLMar 27, 2026

Analysing Calls to Order in German Parliamentary Debates

Authors: Nina Smirnova, Daniel Dan, Philipp Mayr

Organizations: GESIS – Leibniz Institute for the Social Sciences, Germany · Modul University Vienna, Austria

Abstract

Parliamentary debate constitutes a central arena of political power, shaping legislative outcomes and public discourse. Incivility within this arena signals political polarization and institutional conflict. This study presents a systematic investigation of incivility in the German Bundestag by examining calls to order (CtO; plural: CtOs) as formal indicators of norm violations. Despite their relevance, CtOs have received little systematic attention in parliamentary research. We introduce a rule-based method for detecting and annotating CtOs in parliamentary speeches and present a novel dataset of German parliamentary debates spanning 72 years that includes annotated CtO instances. Additionally, we develop the first classification system for CtO triggers and analyze the factors associated with their occurrence. Our findings show that, despite formal regulations, the issuance of CtOs is partly subjective and influenced by session presidents and parliamentary dynamics, with certain individuals disproportionately affected. An insult towards individuals is the most frequent cause of CtO. In general, male members and those belonging to opposition parties receive more calls to order than their female and coalition-party counterparts. Most CtO triggers were detected in speeches dedicated to governmental affairs and actions of the presidency. The CtO triggers dataset is available at: https://github.com/kalawinka/cto_analysis.

Figures & tables

Figure 1: Example of a trigger (red) and an issued call to order (blue). Translated to English from German debates.

	count
total speech contributions	958,098
presidency actions	399,807
speech contributions containing a call to order	558

Table 1: Number of speech contributions and calls to order in GermaParl corpus

class name	description
insult towards individual ( ITO )	insult towards an individual
general insult ( GI )	insult towards a group of people, party, event, actions, etc.
non-verbal ( NV )	non-verbal actions that caused a call to order
not documented verbal ( NDV )	verbal actions that caused a call to order but were not transcribed
miscellaneous ( MISC )	all other verbal actions excluding direct insults that caused a call to order

Table 2: Classification schema.

		total frequency	median per LP	standard deviation
cause	ITO	344	17	18.80
	MISC	120	6	10.54
	GI	106	3	11.20
	NDV	48	2	3.20
	NV	13	1	1.46
party affiliation	opposition	460	10	33.14

Table 3: Total number of speeches containing a specific cause triggered CtO and total number of CtOs distinguished by PCO’s party affiliation in the corpus, and the median frequency by LP.

Figure 2: Distribution of causes, genders and party affiliations of PCOs over legislative periods (LPs).

variable1	variable 2	$\chi^{2}$ statistics	p-value	Cramér’s V
name of the president	name of the PCO	17671.519	0.000	0.795
	gender of the PCO	124.266	0.000	0.462
	party of the PCO	1628.249	0.000	0.464
	cause of the CtO	373.997	0.000	0.400
	PCO’s party affiliation	159.944	0.000	0.524
gender of the president	gender of the PCO	0.003	1.000

Table 4: The

\chi^{2}

test with a Monte Carlo method and Cramér’s V. P-value above the threshold marked with italicized text. A small association is marked with italicized text, a medium association with italicized bold text, and a large association with bold text. Sample size: 583 for variables above the double line; 958,100 for all other variables.

Figure 3: Distribution of the top 10 topics that caused CtOs over legislative periods.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

class name	abbreviation	description	example DE	example EN
insult towards individual	ITO	insult towards an individual	Schreiner [SPD]: Wild gewordener Gartenzwerg!	Schreiner [SPD]: Garden gnome gone wild!
general insult	GI	insult towards a group of people, party, event, actions, etc.	Abg. Renner: Die Union der Faschisten von gestern ist fertig!	PM Renner: The Union of Fascists of yesterday is finished!
non-verbal	NV	non-verbal actions that caused a call to order	Abgeordnete der Fraktion Die Linke halten Transparente und Fahnen hoch.	Members of the parliamentary group Die Linke hold up banners and flags.
not documented verbal	NDV	verbal actions that caused a call to order but were not transcribed.	Der Abg. Dr. Richter [Niedersachsen] wendet sich dem amtierenden Präsidenten zu und spricht unter andauernder großer Unruhe des Hauses auf ihn ein, ohne daß seine Worte vom Haus und am Stenographentisch verstanden werden können.	PM Dr Richter [Lower Saxony] turns to the President-in-Office and speaks to him, to the continued great agitation of the House, without his words being understood by the House and the stenographers’ table.
miscellaneous	MISC	all other verbal actions excluding direct insults that caused a call to order	Gerd Andres [SPD]: Wie lange darf der eigentlich noch reden, Herr Präsident? Ist das unbegrenzt?	Gerd Andres [SPD]: How long is he actually allowed to talk, Mr President? Is that unlimited?

Appendix

Table 5: Classification schema

	count
number of speeches containing a CtO with disambiguated individuals called to order	493
number of speeches containing a CtO with not disambiguated individuals called to order	65

Appendix

Table 6: Number of speech contributions and calls to order in GermaParl corpus

PCO gender	number of PMs called to order	% of PMs called to order	number of PMs in parliamnet	median number of PMs called to order per LP	standard deviation	median % of PMs called to order per LP	standard deviation (%)
male	493	5.25	9390	19	31.99	3.72	7.07
female	59	2.62	2249	5.5	6.57	0	4.99

Appendix

Table 7: Number of PCOs distinguished by their gender.

Political Discourse Analysis

Political discourse analysis studies how language expresses ideology, frames issues, persuades audiences, and shapes political debate.

See all 66 papers

Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach
Apr 23, 2026Flávio Soriano, Victoria F. Mello, Pedro B. Rigueira +4Political Discourse Analysis Computational Social Science
Computer Science Department, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil
Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
Aug 13, 2026Mirko Tritella, Riccardo Pozzi, Matteo PalmonariRetrieval-Augmented Generation Political Discourse Analysis
University of Milano-Bicocca, Milan, Italy
Umm... With Transformers? Insights from Filled Pause Use across Four Slavic Parliaments
Jul 7, 2026Ivan Porupski, Branimir Dropuljić, Nikola Ljubešić
Department of Knowledge Technologies, Joˇzef Stefan Institute, Ljubljana, Slovenia · TransUnion, Zagreb, Croatia · Faculty of Electrical Engineering and Computing, University of Zagreb, Croatia +2

Apr 23, 2026J/K move · Enter open · S save

Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach

Flávio Soriano, Victoria F. Mello, Pedro B. Rigueira, Gisele L. Pappa+3

Computer Science Department, Universidade Federal de Minas Gerais, Belo Horizonte, Minas Gerais, Brazil

Political Discourse Analysis Computational Social Science Semantic Clustering

Open paper AskPDF arXiv

Analyses of legislative behavior often rely on voting records, overlooking the rich semantic and rhetorical content of political speech. In this paper, we ask three complementary questions about parliamentary discourse: how things are said, what is being said, and who is speaking in discursively similar ways. To answer these questions, we introduce a scalable and generalizable computational framework that combines diachronic stylometric analysis, contextual topic modeling, and semantic clustering of deputies' speeches. We apply this framework to a large-scale case study of the Brazilian Chamber of Deputies, using a corpus of over 450,000 speeches from 2003 to 2025. Our results show a long-term stylistic shift toward shorter and more direct speeches, a legislative agenda that reorients sharply in response to national crises, and a granular map of discursive alignments in which regional and gender identities often prove more salient than formal party affiliation. More broadly, this work offers a robust methodology for analyzing parliamentary discourse as a multidimensional phenomenon that complements traditional vote-based approaches.

Abstract

Political Discourse Analysis

Explore similar work

Mapping the Political Discourse in the Brazilian Chamber of Deputies: A Multi-Faceted Computational Approach

Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings

Umm... With Transformers? Insights from Filled Pause Use across Four Slavic Parliaments