Opinionated, Hesitant and Stressed: Three Studies of How Politicians Speak in Four Slavic Parliaments
2026-08-31 • Computation and Language
Computation and Language
AI summaryⓘ
The authors studied spoken political speeches in Croatian, Czech, Polish, and Serbian using a large collection of recordings. They found that negative speech tends to be spoken louder, faster, and with a higher pitch across all four languages. They also discovered patterns in how often speakers use filler sounds like 'um,' which depend on speech speed, age, and emotion, with some differences between South and West Slavic languages. Lastly, they looked at how stress is placed on words in Croatian and found consistent patterns for some word types but not others. They suggest further research in speech sounds, pauses, and political speaking styles.
parliamentary speechsentiment analysisacoustic realisationfilled pausesspeech rateprimary stressSlavic languagesnegative binomial GEEcorpus phoneticsdisfluency
Authors
Ivan Porupski, Nikola Ljubešić
Abstract
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.