@inproceedings{dang-etal-2026-behavioral,
title = "Behavioral Alignment and the Engagement for Non-Speaking Participants in Online Meetings",
author = "Dang, Trung Duc Anh and
Peng, Zhiqing and
Paggio, Patrizia",
editor = "Ghaleb, Esam and
Takmaz, Ece and
Frassinelli, Diego and
Khaertdinov, Bulat and
Fern{\'a}ndez, Raquel and
Yumak, Zerrin and
Ozyurek, Asli",
booktitle = "Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.mint-1.9/",
pages = "78--88",
ISBN = "979-8-89176-482-8",
abstract = "Engagement detection in meetings has focused mostly on speakers, who produce explicit prosodic and acoustic cues. The engagement of non-speaking participants is harder to read because it surfaces only in nonverbal behaviour. We predict how engaged a silent listener is, on a three-level scale (Engaged, Intermittent, Disengaged), in five-second windows of remote Zoom meetings from the GEstures and Head Movements in Language (GEHM) corpus. Each window is described by three feature families: the listener{'}s own nonverbal behaviour, the listener{'}s behavioural alignment with the others present, including the active speaker, and that speaker{'}s prosody. Interpersonal coordination is an established correlate of rapport and involvement. We ask the narrower question of whether a compact window-level alignment measure adds predictive value over listener-only features when confident labels are scarce. Under leakage-free cross-validation, listener-speaker alignment is the most useful addition we test, and the speaker{'}s terminal pitch slope is an interpretable correlate of listener engagement. The gains are modest and their bootstrap intervals include zero. Unsupervised analysis finds no engagement structure. Two findings are firmer: the task is effectively binary, actively engaged versus not, bounded by the scarcity of confident disengaged labels, and the pitch-slope correlate holds despite the small sample."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dang-etal-2026-behavioral">
<titleInfo>
<title>Behavioral Alignment and the Engagement for Non-Speaking Participants in Online Meetings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="given">Duc</namePart>
<namePart type="given">Anh</namePart>
<namePart type="family">Dang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiqing</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Esam</namePart>
<namePart type="family">Ghaleb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Frassinelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bulat</namePart>
<namePart type="family">Khaertdinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raquel</namePart>
<namePart type="family">Fernández</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zerrin</namePart>
<namePart type="family">Yumak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asli</namePart>
<namePart type="family">Ozyurek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-482-8</identifier>
</relatedItem>
<abstract>Engagement detection in meetings has focused mostly on speakers, who produce explicit prosodic and acoustic cues. The engagement of non-speaking participants is harder to read because it surfaces only in nonverbal behaviour. We predict how engaged a silent listener is, on a three-level scale (Engaged, Intermittent, Disengaged), in five-second windows of remote Zoom meetings from the GEstures and Head Movements in Language (GEHM) corpus. Each window is described by three feature families: the listener’s own nonverbal behaviour, the listener’s behavioural alignment with the others present, including the active speaker, and that speaker’s prosody. Interpersonal coordination is an established correlate of rapport and involvement. We ask the narrower question of whether a compact window-level alignment measure adds predictive value over listener-only features when confident labels are scarce. Under leakage-free cross-validation, listener-speaker alignment is the most useful addition we test, and the speaker’s terminal pitch slope is an interpretable correlate of listener engagement. The gains are modest and their bootstrap intervals include zero. Unsupervised analysis finds no engagement structure. Two findings are firmer: the task is effectively binary, actively engaged versus not, bounded by the scarcity of confident disengaged labels, and the pitch-slope correlate holds despite the small sample.</abstract>
<identifier type="citekey">dang-etal-2026-behavioral</identifier>
<location>
<url>https://aclanthology.org/2026.mint-1.9/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>78</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Behavioral Alignment and the Engagement for Non-Speaking Participants in Online Meetings
%A Dang, Trung Duc Anh
%A Peng, Zhiqing
%A Paggio, Patrizia
%Y Ghaleb, Esam
%Y Takmaz, Ece
%Y Frassinelli, Diego
%Y Khaertdinov, Bulat
%Y Fernández, Raquel
%Y Yumak, Zerrin
%Y Ozyurek, Asli
%S Proceedings of the 1st Workshop on Multimodal Interaction in Face-to-Face Dialogue
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-482-8
%F dang-etal-2026-behavioral
%X Engagement detection in meetings has focused mostly on speakers, who produce explicit prosodic and acoustic cues. The engagement of non-speaking participants is harder to read because it surfaces only in nonverbal behaviour. We predict how engaged a silent listener is, on a three-level scale (Engaged, Intermittent, Disengaged), in five-second windows of remote Zoom meetings from the GEstures and Head Movements in Language (GEHM) corpus. Each window is described by three feature families: the listener’s own nonverbal behaviour, the listener’s behavioural alignment with the others present, including the active speaker, and that speaker’s prosody. Interpersonal coordination is an established correlate of rapport and involvement. We ask the narrower question of whether a compact window-level alignment measure adds predictive value over listener-only features when confident labels are scarce. Under leakage-free cross-validation, listener-speaker alignment is the most useful addition we test, and the speaker’s terminal pitch slope is an interpretable correlate of listener engagement. The gains are modest and their bootstrap intervals include zero. Unsupervised analysis finds no engagement structure. Two findings are firmer: the task is effectively binary, actively engaged versus not, bounded by the scarcity of confident disengaged labels, and the pitch-slope correlate holds despite the small sample.
%U https://aclanthology.org/2026.mint-1.9/
%P 78-88
Markdown (Informal)
[Behavioral Alignment and the Engagement for Non-Speaking Participants in Online Meetings](https://aclanthology.org/2026.mint-1.9/) (Dang et al., MINT 2026)
ACL