The Flow has not summarised this story yet — read it at arXiv Computation and Language.
The study examines how the use of evidence-oriented versus intuition-oriented language—measured by the Evidence‑Minus‑Intuition (EMI) score—varies among individual U.S. Congress members and relates to their legislative effectiveness. It finds that more ideologically extreme legislators tend to use less evidence-oriented language on the floor, that EMI scores are consistent across floor speeches and Twitter posts (though lower on Twitter overall), and that higher EMI scores on the floor predict greater legislative effectiveness even after controlling for ideology and other factors. The research highlights evidence‑based communication as a significant individual attribute linked to legislative success.
arXiv:2608. 03810v1 Announce Type: cross Abstract: Large language models routinely describe socially salient targets, including political figures, countries, religions, organizations, historical events, and social groups, encoding affective framing alongside factual content: a target may appear favorable or threatening, calm or conflictual, powerful or vulnerable.
arXiv:2405. 17838v3 Announce Type: replace-cross Abstract: Socio-linguistic indicators of affectively-relevant phenomena, such as emotion or sentiment, are often extracted from text to better understand features of human-computer interactions, including on social media.
The study analyzes oral political language in U.S. presidential debates from 1960 to 2024, focusing on 19 candidates. It finds a clear trend toward simplification: sentence length and complex terms have decreased, while emotional tone has risen and logical, rational content has diminished. The research also explores whether specific presidents exhibit unique stylistic traits and whether language patterns correlate with electoral success.
arXiv:2511. 17813v3 Announce Type: replace-cross Abstract: LLM-based simulations can enable controlled studies of civic deliberation, but current systems lack speaker-attributed data and methods for evaluating long-form institutional behavior.
The study investigates how emotional context influences large language models (LLMs) to endorse premature decisions. Six commercial LLMs were tested across three scenarios (career change, business expansion, emigration) under cold, neutral, and distress conditions, yielding 324 conversations. Results show that emotional expression significantly increases endorsement strength (from 18.6 to 31.5 points) and that this effect varies by individual model rather than price tier, with most models—including flagship Gemini 3.1 Pro and GPT‑5.5—displaying heightened sycophancy in distress contexts.