Transcript-based interactional fluency and direction-sensitive uptake analysis

Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 causal), q3 · 1 of 1 report an effect size · 2 claims rest on one study

Description

A reusable analysis pipeline that operationalizes interactional fluency and direction-sensitive linguistic uptake for spoken AI practice "using metrics extractable from diarized ASR output without manual linguistic annotation." The fluency component extracts seven features from word-level timestamps (conversation length, turn count, mean turn duration, words per turn, response latency, floor ratio, within-turn pause ratio). The uptake component tracks lexical adoption via a global timeline with a first-use, first-source-wins rule, and syntactic uptake via four German morphosyntactic template types parsed with the Stanza UD pipeline, with correctness checked against a 91,270-noun gender lexicon. The authors provide it as "a reusable analysis pipeline for rapid, scalable evaluation of conversational AI in educational settings."

Accounts

• Transcript-based pipeline for measuring interactional fluency and direction-sensitive uptake from diarized ASR output: A reusable analysis pipeline that operationalizes interactional fluency and direction-sensitive linguistic uptake for spoken AI practice "using metrics extractable from diarized ASR output without manual linguistic annotation." The fluency component extracts seven features from word-level timestamps (conversation length, turn count, mean turn duration, words per turn, response latency, floor ratio, within-turn pause ratio). The uptake component tracks lexical adoption via a global timeline with a first-use, first-source-wins rule, and syntactic uptake via four German morphosyntactic template types parsed with the Stanza UD pipeline, with correctness checked against a 91,270-noun gender lexicon. The authors provide it as "a reusable analysis pipeline for rapid, scalable evaluation of conversational AI in educational settings." (Russell Scheinberg et al. (2026))

Claims

• Learners show stronger short-term syntactic priming with the AI partner, significant across all three recency-window operationalizations including one equalizing input volume [+W]
• Lexical adoption shows no significant condition effect after controlling for input volume, but AI-first participants adopted more words at the second dialogue position [+W]

Related Research Methods

• Two-metric turn-level evaluation of chatbot scaffolding and student uptake

Key Sources

• Russell Scheinberg, Ameeta Agrawal, Tetyana Sydorenko, Kalab Kahsay, Nina Vyatkina, Griet Boone. (2026). What Changes When the Interlocutor Is an AI? Interactional Fluency and Linguistic Uptake in L2 Spoken Dialogue. https://arxiv.org/abs/2606.22225

Page metadata

Field	Value
type	research-method
id	transcript-based-interactional-fluency-and-direction-sensitive-uptake-analysis
title	Transcript-based interactional fluency and direction-sensitive uptake analysis
description	A reusable analysis pipeline that operationalizes interactional fluency and direction-sensitive linguistic uptake for spoken AI practice "using metrics extractable from diarized ASR output without manual linguistic annotation." The fluency component extracts seven features from word-level timestamps
status	review
generated	by process:settle-candidates on 2026-10-10
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.