The Interplay of Paralinguistic Cues and Expressions of Certainty in Human-Human and Human-Agent Interactions

There is limited understanding of how paralinguistic cues relate to expressions of certainty in human-agent vs. human-human interactions. We collected data through two phases: (1) we analyzed the pronunciation of phrases from participants across different interaction scenarios and with different certainty levels to establish what cues people use to express certainty; and (2) through an online survey, we presented participants with recordings of humans and agents uttering phrases across different scenarios, and asked participants to identify the certainty level of each recording. We found that it is easier for people to express and recognize low certainty consistently, vs. high certainty, in both human-human and human-agent interactions. Additionally, people tend to rate utterances from agents with lower certainty than humans, even when using the same cues. We contribute design recommendations for agents using paralinguistic cues to express varying levels of certainty across different interaction contexts.

Authors

Institutions

Publication Details

Journal
ACM Transactions on Computer-Human Interaction
Published
2026-07-18
DOI
https://doi.org/10.1145/3830401
Primary Topic
Social Robot Interaction and HRI
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

The Interplay of Paralinguistic Cues and Expressions of Certainty in Human-Human and Human-Agent Interactions

Brennan Jones, Manveer Kalirai, Young‐Ho Kim, Anastasia Kuzminykh et al.
ACM Transactions on Computer-Human Interaction
Social Robot Interaction and HRI
article

The Interplay of Paralinguistic Cues and Expressions of Certainty in Human-Human and Human-Agent Interactions

Brennan Jones, Manveer Kalirai, Young‐Ho Kim, Anastasia Kuzminykh, Peter Dushniku, Emily Su, Annie Tan, Christina Wei
article en

Abstract

There is limited understanding of how paralinguistic cues relate to expressions of certainty in human-agent vs. human-human interactions. We collected data through two phases: (1) we analyzed the pronunciation of phrases from participants across different interaction scenarios and with different certainty levels to establish what cues people use to express certainty; and (2) through an online survey, we presented participants with recordings of humans and agents uttering phrases across different scenarios, and asked participants to identify the certainty level of each recording. We found that it is easier for people to express and recognize low certainty consistently, vs. high certainty, in both human-human and human-agent interactions. Additionally, people tend to rate utterances from agents with lower certainty than humans, even when using the same cues. We contribute design recommendations for agents using paralinguistic cues to express varying levels of certainty across different interaction contexts.

ACM Transactions on Computer-Human Interaction
University of Toronto (CA), NAVER Cloud (South Korea) (KR), Naver (South Korea) (KR), Xi’an Jiaotong-Liverpool University (CN)
Quality Education
Openalex Percentile: Top 5%
Social Robot Interaction and HRI
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

The Interplay of Paralinguistic Cues and Expressions of Certainty in Human-Human and Human-Agent Interactions — Brennan Jones, Manveer Kalirai, et al. · ACM Transactions on Computer-Human Interaction (2026) | TGRS Research Map | TGRS