Exploring effects of conversational fillers on user perception of conversational agents

Yuin Jeong, Youn Ah Kang, Juho Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Through technological advancements in various areas of our lives, Conversational Agents progressed in their human-likeness. In the field of HCI, however, the use of conversational fillers (e.g., “um,” “uh,” etc.) by Conversational Agents have not been fully explored in an experimental setting. We observed the effects on user perceptions of Intelligence, Human-likeness and Likability of Conversational Agents by a 2 x 2 experimental design. From the results of 26 total participants, we concluded that 1) the use of fillers by Conversational Agents are perceived as less intelligent and less likable in task-oriented conversations, 2) and the fillers did not have any statistically significant change in perception of human-likeness. However, further examination showed that users reported filler-speaking agents as more entertaining for social-oriented conversations. With these findings, we discuss design implications for voice-based Conversational Agents.

Original languageEnglish
Title of host publicationCHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450359719
DOIs
Publication statusPublished - 2019 May 2
Event2019 CHI Conference on Human Factors in Computing Systems, CHI EA 2019 - Glasgow, United Kingdom
Duration: 2019 May 42019 May 9

Publication series

NameConference on Human Factors in Computing Systems - Proceedings

Conference

Conference2019 CHI Conference on Human Factors in Computing Systems, CHI EA 2019
CountryUnited Kingdom
CityGlasgow
Period19/5/419/5/9

Fingerprint

Fillers
Human computer interaction
Design of experiments

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Cite this

Jeong, Y., Kang, Y. A., & Lee, J. (2019). Exploring effects of conversational fillers on user perception of conversational agents. In CHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems [3312913] (Conference on Human Factors in Computing Systems - Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3290607.3312913
Jeong, Yuin ; Kang, Youn Ah ; Lee, Juho. / Exploring effects of conversational fillers on user perception of conversational agents. CHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2019. (Conference on Human Factors in Computing Systems - Proceedings).
@inproceedings{c4235e2574b04cb1a819b6235e2881ce,
title = "Exploring effects of conversational fillers on user perception of conversational agents",
abstract = "Through technological advancements in various areas of our lives, Conversational Agents progressed in their human-likeness. In the field of HCI, however, the use of conversational fillers (e.g., “um,” “uh,” etc.) by Conversational Agents have not been fully explored in an experimental setting. We observed the effects on user perceptions of Intelligence, Human-likeness and Likability of Conversational Agents by a 2 x 2 experimental design. From the results of 26 total participants, we concluded that 1) the use of fillers by Conversational Agents are perceived as less intelligent and less likable in task-oriented conversations, 2) and the fillers did not have any statistically significant change in perception of human-likeness. However, further examination showed that users reported filler-speaking agents as more entertaining for social-oriented conversations. With these findings, we discuss design implications for voice-based Conversational Agents.",
author = "Yuin Jeong and Kang, {Youn Ah} and Juho Lee",
year = "2019",
month = "5",
day = "2",
doi = "10.1145/3290607.3312913",
language = "English",
series = "Conference on Human Factors in Computing Systems - Proceedings",
publisher = "Association for Computing Machinery",
booktitle = "CHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems",

}

Jeong, Y, Kang, YA & Lee, J 2019, Exploring effects of conversational fillers on user perception of conversational agents. in CHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems., 3312913, Conference on Human Factors in Computing Systems - Proceedings, Association for Computing Machinery, 2019 CHI Conference on Human Factors in Computing Systems, CHI EA 2019, Glasgow, United Kingdom, 19/5/4. https://doi.org/10.1145/3290607.3312913

Exploring effects of conversational fillers on user perception of conversational agents. / Jeong, Yuin; Kang, Youn Ah; Lee, Juho.

CHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, 2019. 3312913 (Conference on Human Factors in Computing Systems - Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Exploring effects of conversational fillers on user perception of conversational agents

AU - Jeong, Yuin

AU - Kang, Youn Ah

AU - Lee, Juho

PY - 2019/5/2

Y1 - 2019/5/2

N2 - Through technological advancements in various areas of our lives, Conversational Agents progressed in their human-likeness. In the field of HCI, however, the use of conversational fillers (e.g., “um,” “uh,” etc.) by Conversational Agents have not been fully explored in an experimental setting. We observed the effects on user perceptions of Intelligence, Human-likeness and Likability of Conversational Agents by a 2 x 2 experimental design. From the results of 26 total participants, we concluded that 1) the use of fillers by Conversational Agents are perceived as less intelligent and less likable in task-oriented conversations, 2) and the fillers did not have any statistically significant change in perception of human-likeness. However, further examination showed that users reported filler-speaking agents as more entertaining for social-oriented conversations. With these findings, we discuss design implications for voice-based Conversational Agents.

AB - Through technological advancements in various areas of our lives, Conversational Agents progressed in their human-likeness. In the field of HCI, however, the use of conversational fillers (e.g., “um,” “uh,” etc.) by Conversational Agents have not been fully explored in an experimental setting. We observed the effects on user perceptions of Intelligence, Human-likeness and Likability of Conversational Agents by a 2 x 2 experimental design. From the results of 26 total participants, we concluded that 1) the use of fillers by Conversational Agents are perceived as less intelligent and less likable in task-oriented conversations, 2) and the fillers did not have any statistically significant change in perception of human-likeness. However, further examination showed that users reported filler-speaking agents as more entertaining for social-oriented conversations. With these findings, we discuss design implications for voice-based Conversational Agents.

UR - http://www.scopus.com/inward/record.url?scp=85067308545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067308545&partnerID=8YFLogxK

U2 - 10.1145/3290607.3312913

DO - 10.1145/3290607.3312913

M3 - Conference contribution

T3 - Conference on Human Factors in Computing Systems - Proceedings

BT - CHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems

PB - Association for Computing Machinery

ER -

Jeong Y, Kang YA, Lee J. Exploring effects of conversational fillers on user perception of conversational agents. In CHI EA 2019 - Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery. 2019. 3312913. (Conference on Human Factors in Computing Systems - Proceedings). https://doi.org/10.1145/3290607.3312913