Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment

Sumit Srivastava; Mariet Theune; Alejandro Catalá; Chris Reed

doi:10.1145/3631700.3664868

Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment

Sumit Srivastava
, Mariet Theune
, Alejandro Catalá
, Chris Reed

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

6 Citations (Scopus)

345 Downloads (Pure)

Abstract

Lexical alignment is a form of personalization frequently found in human-human conversations. Recently, attempts have been made to incorporate it in human-computer conversations. We describe an experiment to investigate the trust of users in the performance of a conversational agent that lexically aligns or misaligns, in a collaborative task. The participants performed a travel planning task with the help of the agent, involving rescuing residents and minimizing the travel path on a fictional map. We found that trust in the conversational agent was not significantly affected by the alignment capability of the agent.

Original language	English
Title of host publication	UMAP Adjunct '24: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization
Publisher	Association for Computing Machinery
Pages	189-194
Number of pages	6
ISBN (Electronic)	979-8-4007-0466-6
DOIs	https://doi.org/10.1145/3631700.3664868
Publication status	Published - 28 Jun 2024
Event	32nd ACM Conference on User Modeling, Adaptation and Personalization, ACM UMAP 2024 - Cagliari, Italy Duration: 1 Jul 2024 → 4 Jul 2024 Conference number: 32 https://www.um.org/umap2024/

Conference

Conference	32nd ACM Conference on User Modeling, Adaptation and Personalization, ACM UMAP 2024
Abbreviated title	ACM UMAP 2024
Country/Territory	Italy
City	Cagliari
Period	1/07/24 → 4/07/24
Internet address	https://www.um.org/umap2024/

Keywords

lexical alignment
human-agent interaction
conversational agents
performance trust

Access to Document

10.1145/3631700.3664868

UMAP_camera_ready_Alignment_Trust FINALAccepted author version, 1.28 MB

Cite this

@inproceedings{a2fc18d922524dec9636ed29d34e95c0,

title = "Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment",

abstract = "Lexical alignment is a form of personalization frequently found in human-human conversations. Recently, attempts have been made to incorporate it in human-computer conversations. We describe an experiment to investigate the trust of users in the performance of a conversational agent that lexically aligns or misaligns, in a collaborative task. The participants performed a travel planning task with the help of the agent, involving rescuing residents and minimizing the travel path on a fictional map. We found that trust in the conversational agent was not significantly affected by the alignment capability of the agent.",

keywords = "lexical alignment, human-agent interaction, conversational agents, performance trust",

author = "Sumit Srivastava and Mariet Theune and Alejandro Catal{\'a} and Chris Reed",

year = "2024",

month = jun,

day = "28",

doi = "10.1145/3631700.3664868",

language = "English",

pages = "189--194",

booktitle = "UMAP Adjunct '24: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization",

publisher = "Association for Computing Machinery",

address = "United States",

note = "32nd ACM Conference on User Modeling, Adaptation and Personalization, ACM UMAP 2024, ACM UMAP 2024 ; Conference date: 01-07-2024 Through 04-07-2024",

url = "https://www.um.org/umap2024/",

}

Srivastava, S, Theune, M, Catalá, A & Reed, C 2024, Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment. in UMAP Adjunct '24: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery, pp. 189-194, 32nd ACM Conference on User Modeling, Adaptation and Personalization, ACM UMAP 2024, Cagliari, Italy, 1/07/24. https://doi.org/10.1145/3631700.3664868

Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment. / Srivastava, Sumit; Theune, Mariet; Catalá, Alejandro et al.
UMAP Adjunct '24: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization. Association for Computing Machinery, 2024. p. 189-194.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment

AU - Srivastava, Sumit

AU - Theune, Mariet

AU - Catalá, Alejandro

AU - Reed, Chris

N1 - Conference code: 32

PY - 2024/6/28

Y1 - 2024/6/28

N2 - Lexical alignment is a form of personalization frequently found in human-human conversations. Recently, attempts have been made to incorporate it in human-computer conversations. We describe an experiment to investigate the trust of users in the performance of a conversational agent that lexically aligns or misaligns, in a collaborative task. The participants performed a travel planning task with the help of the agent, involving rescuing residents and minimizing the travel path on a fictional map. We found that trust in the conversational agent was not significantly affected by the alignment capability of the agent.

AB - Lexical alignment is a form of personalization frequently found in human-human conversations. Recently, attempts have been made to incorporate it in human-computer conversations. We describe an experiment to investigate the trust of users in the performance of a conversational agent that lexically aligns or misaligns, in a collaborative task. The participants performed a travel planning task with the help of the agent, involving rescuing residents and minimizing the travel path on a fictional map. We found that trust in the conversational agent was not significantly affected by the alignment capability of the agent.

KW - lexical alignment

KW - human-agent interaction

KW - conversational agents

KW - performance trust

U2 - 10.1145/3631700.3664868

DO - 10.1145/3631700.3664868

M3 - Conference contribution

SP - 189

EP - 194

BT - UMAP Adjunct '24: Adjunct Proceedings of the 32nd ACM Conference on User Modeling, Adaptation and Personalization

PB - Association for Computing Machinery

T2 - 32nd ACM Conference on User Modeling, Adaptation and Personalization, ACM UMAP 2024

Y2 - 1 July 2024 through 4 July 2024

ER -

Trust in a Human-Computer Collaborative Task With or Without Lexical Alignment

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this