Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations

Sarah Sulollari; Vanja Karan; Benjamin Roth

cs.CLOct 23, 2026

Analysing Austrian Parliamentary Speeches by Predicting Party Affiliations

Authors: Sarah Sulollari, Vanja Karan, Benjamin Roth

Organizations: University of Vienna

Abstract

This paper examines speech characteristics of the Austrian National Council members (CMs). We introduce analysis methodology based on a fine-tuned BERT-Model which assigns to every speech a probability distribution over Austrian parties. These are then aggregated at the speaker and party level. We perform an extensive evaluation to ensure the quality of the generated distributions prior to further analysis. Instead of considering mis-assignments of predicted parties as a performance issue, we leverage them to derive insights about the CMs and political developments. Our findings show that parties that govern together become more similar in their speech characteristics, while, analogously, parties that are in opposition move further away from governing parties. Moreover, CMs who switch party usually adapt their speech characteristics only after the switch occurs. Finally, we publicly release a data set containing party affiliation predictions for the speeches of the Austrian National Council from 1996 to 2018.

Figures & tables

Party	Political Leaning
SPÖ	centre left
ÖVP	centre right
FPÖ	right
GRÜNE	centre left
LIF	centre right
BZÖ	right

Table 1: Rough estimation of political parties in data set

Figure 1: Distribution of Speeches across all parties

Figure 2: Distribution of speakers across parties.

Figure 3: Number of CMs joining or leaving a party.

Party	Precision	Recall	F1	Support
SPÖ	0.53	0.57	0.55	12109
ÖVP	0.57	0.59	0.58	11477
FPÖ	0.49	0.58	0.54	9736
GRÜNE	0.60	0.45	0.51	7856
LIF	0.43	0.31	0.35	1430
BZÖ	0.33	0.31	0.32	2389

Table 2: Average scores per speech aggregated per party

Party	Precision	Recall	F1	Support
SPÖ	0.61	0.64	0.62	24218
ÖVP	0.63	0.65	0.64	23428
FPÖ	0.55	0.66	0.60	16766
GRÜNE	0.67	0.53	0.59	12093
LIF	0.51	0.37	0.43	1869
BZÖ	0.40	0.34	0.36	4108

Table 3: Scores for speeches >30 tokens

Party	Precision	Recall	F1
SPÖ	0,89	0,89	0,89
ÖVP	0,85	0,95	0,90
FPÖ	0,86	0,90	0,88
GRÜNE	0,86	0,84	0,85
LIF	0,83	0,42	0,56
BZÖ	0,78	0,44	0,56

Table 4: Scores when aggregating the speech predictions the CM level

Party	Precision	Recall	F1
SPÖ	0,74	0,82	0,78
ÖVP	0,82	0,90	0,86
FPÖ	0,84	0,91	0,87
GRÜNE	0,77	0,68	0,72
LIF	1	0,36	0,53
BZÖ	1	0,11	0,19

Table 5: Scores when aggregating the speech predictions the CM level - Logistic Regression

Party	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS
SPÖ	185	19	0	2	0	0	1
ÖVP	6	211	5	0	0	0	0
FPÖ	2	15	157	0	1	0	0
GRÜNE	6	1	0	37	0	0	0
LIF	3	0	2	2	5	0	0
BZÖ	0	1	8	0	0	7	0

Table 6: Predicted party (columns) and actual party (rows)

Figure 5: Probability of speeches being FPÖ(blue) and BZÖ(orange) over time. The box shows the time of creation of the BZÖ and the slow rise in speeches being predicted as BZÖ over time.

Figure 6: Proportion of SPÖ speeches being classified as ÖVP or FPÖ

Figure 7: Proportion of ÖVP speeches being classified as ÖVP or FPÖ

Figure 8: Proportion of FPÖ speeches being classified as ÖVP or FPÖ

Figure 9: Proportion of GRÜNE speeches being classified as ÖVP or FPÖ

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Alexander Zach	0.26	0.07	0.05	0.23	0.04	0.01	0.26	0.01	0.06	NEOS
Heinz Fischer	0.22	0.14	0.15	0.45	0.04	0.00	0.00	0.00	0.00	GRÜNE
Ulrike Sima	0.29	0.04	0.16	0.47	0.00	0.03	0.00	0.00	0.00	GRÜNE
Alois Stöger	0.37	0.53	0.07	0.01	0.00	0.01	0.00	0.00	0.00	ÖVP
Andrea Gessl-Ranftl	0.42	0.44	0.06	0.03	0.00	0.03	0.00	0.01	0.00	ÖVP
Christian Hursky	0.32	0.46	0.14	0.04	0.00	0.02	0.01	0.00	0.00	ÖVP

Table 7: Party affiliation score of misclassified SPÖ members

Figure 10: Probability distribution of speeches

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Franz Steindl	0.38	0.12	0.04	0.03	0.00	0.00	0.00	0.00	0.00	SPÖ
Hannes Farnleitner	0.33	0.03	0.01	0.05	0.00	0.00	0.00	0.00	0.00	SPÖ
Joseph Huainigg	0.3	0.1	0.14	0.00	0.07	0.01	0.03	0.01	0.00	SPÖ
Juliane Bogner-Strauß	0.4	0.06	0.03	0.00	0.02	0.02	0.01	0.01	0.00	SPÖ
Kira Grünberg	0.34	0.12	0.06	0.00	0.01	0.01	0.01	0.02	0.00	SPÖ
Werner Fasslabend	0.34	0.15	0.02	0.02	0.01	0.00	0.00	0.00	0.00	SPÖ

Table 8: Party affiliation score of misclassified ÖVP members

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Franz Löschnak	0.61	0.14	0.12	0.05	0.07	0.00	0.00	0.00	0.00	SPÖ
Hans Müller	0.39	0.24	0.36	0.00	0.00	0.00	0.00	0.00	0.00	SPÖ
Alois Kainz	0.3	0.34	0.33	0.01	0.00	0.01	0.01	0.01	0.00	ÖVP
Christian Pewny	0.16	0.43	0.38	0.02	0.00	0.01	0.00	0.00	0.00	ÖVP
Christian Ragger	0.26	0.44	0.18	0.00	0.00	0.04	0.06	0.00	0.00	ÖVP
Christian Ries	0.14	0.45	0.32	0.00	0.00	0.06	0.00	0.01	0.01	ÖVP

Table 9: Party affiliation score of misclassified FPÖ members

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Berivan Aslan	0.32	0.12	0.09	0.23	0.00	0.04	0.12	0.03	0.05	SPÖ
Bettina Hradecsni	0.33	0.15	0.18	0.26	0.00	0.04	0.02	0.02	0.01	SPÖ
Heidemarie Rest-Hinterseer	0.37	0.08	0.13	0.36	0.00	0.03	0.03	0.01	0.00	SPÖ
Johannes Voggenhuber	0.49	0.09	0.03	0.22	0.17	0.00	0.00	0.00	0.00	SPÖ
Kurt Grünewald	0.28	0.14	0.2	0.25	0.01	0.06	0.02	0.03	0.01	SPÖ
Wolfgang Pirklhuber	0.4	0.08	0.1	0.33	0.01	0.05	0.01	0.01	0.01	SPÖ

Table 10: Party affiliation score of misclassified GRÜNE members

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Friedhelm Frischenschlager	0.26	0.11	0.24	0.16	0.23	0	0	0	0	SPÖ
Helmut Moser	0.36	0.16	0.19	0.07	0.2	0.01	0	0	0	SPÖ
Helmut Peter	0.19	0.17	0.29	0.12	0.22	0	0	0	0	FPÖ
Maria Schaffenrath	0.19	0.09	0.24	0.25	0.22	0.01	0	0	0	GRÜNE
Peter Haselsteiner	0.15	0.11	0.31	0.14	0.3	0	0	0	0	FPÖ
Rosa Mlinar	0.29	0.26	0.05	0.03	0.01	0.02	0.28	0.03	0.04	SPÖ

Table 11: Party affiliation score of misclassified LIF members

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Ernest Windholz	0.14	0.14	0.4	0.04	0	0.22	0.01	0.04	0	FPÖ
Gerhard Huber	0.11	0.07	0.38	0.03	0	0.34	0	0.06	0	FPÖ
Hubert Gorbach	0.12	0.42	0.39	0.02	0	0.04	0	0	0	ÖVP
Karin Gastinger	0.18	0.32	0.46	0.01	0	0.02	0	0	0	FPÖ
Peter Westenthaler	0.08	0.12	0.4	0.09	0	0.29	0.01	0.01	0	FPÖ
Sigisbert Dolinschek	0.16	0.12	0.49	0.03	0	0.18	0.01	0.01	0	FPÖ

Table 12: Party affiliation score of misclassified BZÖ members

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Christoph Vavrik	0.16	0.16	0.21	0.17	0.01	0.05	0.13	0.06	0.04	FPÖ
Gerald Loacker	0.18	0.11	0.27	0.12	0.01	0.09	0.16	0.05	0.02	FPÖ
Irmgard Griss	0.28	0.14	0.13	0.24	0.02	0.05	0.09	0.01	0.06	SPÖ
Josef Schellhorn	0.1	0.15	0.32	0.08	0.01	0.05	0.17	0.1	0.02	FPÖ
Nikolaus Scherak	0.15	0.06	0.24	0.24	0	0.07	0.19	0.01	0.04	GRÜNE

Table 13: Party affiliation score of misclassified NEOS members

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Elisabeth Kaufmann-Bruckberger	0.17	0.16	0.43	0.01	0	0.18	0	0.05	0	FPÖ
Erich Tadler	0.2	0.12	0.23	0.02	0	0.26	0	0.16	0	BZÖ
Georg Vetter	0.14	0.26	0.31	0.08	0.01	0.06	0.05	0.1	0.01	FPÖ
Leopold Steinbichler	0.2	0.2	0.33	0.05	0	0.07	0.04	0.1	0.01	FPÖ
Martina Schenk	0.11	0.06	0.24	0.05	0	0.33	0.02	0.17	0.01	BZÖ
Robert Lugar	0.05	0.04	0.3	0.05	0	0.29	0.03	0.23	0.01	FPÖ

Table 14: Party affiliation score of misclassified STRONACH members

Speaker	SPÖ	ÖVP	FPÖ	GRÜNE	LIF	BZÖ	NEOS	TS	PILZ	predicted
Alfred J. Noll	0.17	0.1	0.24	0.28	0.01	0.03	0.13	0.02	0.04	GRÜNE
Alma Zadic	0.23	0.14	0.11	0.15	0	0.03	0.17	0.05	0.12	SPÖ
Daniela Holzinger-Vogtenhuber	0.41	0.1	0.08	0.16	0	0.02	0.09	0.08	0.04	SPÖ
Martha Bißmann	0.28	0.14	0.09	0.13	0	0.03	0.13	0.02	0.17	SPÖ
Peter Kolba	0.37	0.17	0.12	0.09	0	0.03	0.07	0.07	0.1	SPÖ
Stephanie Cox	0.31	0.11	0.09	0.2	0	0.01	0.18	0.04	0.05	SPÖ

Table 15: Party affiliation score of misclassified PILZ members

Political Discourse Analysis

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

See all 66 papers

Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments
Aug 31, 2026Ivan Porupski, Nikola LjubešićPolitical Discourse Analysis Speech Prosody
Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia · Institute of Contemporary History, Ljubljana, Slovenia · Faculty of Computer and Information Science, University of Ljubljana, Slovenia
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
Who Would You Vote For? Auditing Political Alignment in LLMs: An Italian Case-Study
Aug 12, 2026Simone MungariLLM Auditing Political Bias in Language Models
Revelis s.r.l.

Aug 31, 2026J/K move · Enter open · S save

Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments

Ivan Porupski, Nikola Ljubešić

Department of Knowledge Technologies, Jožef Stefan Institute, Ljubljana, Slovenia · Institute of Contemporary History, Ljubljana, Slovenia · Faculty of Computer and Information Science, University of Ljubljana, Slovenia

Political Discourse Analysis Speech Prosody

Open paper AskPDF arXiv

We present three large-scale studies of spoken parliamentary speech across four Slavic languages (Croatian, Czech, Polish, Serbian), drawing on over 6,000 hours from the ParlaSpeech 3.0 corpus. The first study examines how utterance-level sentiment shapes acoustic realisation: negative speech is consistently produced with higher pitch, greater intensity, and faster rate across all four parliaments, with a secondary arousal-driven upturn at the most positive extreme. The second study models filled pause frequency using negative binomial GEE, finding that speech rate, age, and sentiment are robust cross-lingual predictors, while gender effects reverse between South Slavic (men produce fewer filled pauses) and West Slavic parliaments (no gender difference) - a pattern invisible to single-language designs. The third study investigates primary stress variation in Croatian, showing that speaker-level preferences for early versus late stress cohere across verbs, adjectives, and nouns but decouple for adverbs and proper nouns. We conclude with a research agenda spanning corpus phonetics, disfluency modelling, and political rhetoric.

Abstract

Political Discourse Analysis

Explore similar work

Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments

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

Who Would You Vote For? Auditing Political Alignment in LLMs: An Italian Case-Study