Beyond Acoustic Emotion Recognition: Multimodal Pathos Analysis in Political Speech Using LLM-Based and Acoustic Emotion Models
arXiv:2605.22732v1 Announce Type: cross Abstract: We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationalised by the TRUST multi-agent large language model (LLM) pipeline. Using a Bundestag plenary speech by Felix Banaszak (51 segments, 245 s) as a case study, we compare three analysis modalities: (1) emotion2vec_plus_large, an acoustic speech emotion recognition (SER) model whose continuous Arousal and Valence values are derived via post-hoc Russell Circumplex projection; (2) Gemini 2.5 Flash, an LLM
The proliferation of advanced LLMs and multimodal AI capabilities enables new forms of complex analysis, such as inferring pathos from political speech, which was previously challenging.
This development allows for more granular and automated analysis of political rhetoric, offering insights into emotional manipulation and persuasive strategies at scale for political analysts, strategists, and public opinion researchers.
The ability to scientifically quantify and analyze the 'pathos' dimension of political communication, bridging the gap between acoustic cues and psychological impact, will enhance predictive models of political outcomes.
- · AI/ML researchers
- · Political science departments
- · Public relations firms
- · Social media analytics platforms
- · Traditional qualitative political analysis
- · Propagandists relying on opaque emotional appeals
Automated pathos analysis becomes a standard tool for evaluating political communication.
Political campaigns begin 'pathos-engineering' speeches and broadcasts for maximum emotional impact, leading to a new arms race in emotional persuasion.
Enhanced public awareness and education on emotional manipulation tactics in political discourse, potentially leading to a more discerning electorate or a backlash against overt emotional appeals.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL