kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Don't walk between us: adherence to social conventions when joining a small conversational group of agents
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Computational Science and Technology (CST).ORCID iD: 0000-0001-5634-8960
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Computational Science and Technology (CST).ORCID iD: 0000-0003-4689-4647
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Computational Science and Technology (CST).ORCID iD: 0000-0002-7257-0761
2022 (English)In: IVA '22: Proceedings of the 22nd ACM International Conference on Intelligent Virtual Agents, New York,NY,USA: Association for Computing Machinery (ACM), 2022Conference paper, Published paper (Refereed)
Abstract [en]

When modeling life-like Embodied Conversational Agents (ECAs), conveying politeness through verbal and nonverbal behaviors with persuasive intents is a significant challenge, as it underlies the conventional set of behavioral rules that govern human communication. In the present study, we explore the adherence to such rules in the context of joining a small, freestanding conversational group of agents in VR. In particular, we focus on the behavior adopted by participants while walking towards the agents, and on whether ECAs were treated in the same way human agents normally are. 45 test subjects were invited by an ECA to walk towards the group by applying one of six possible politeness strategies; after freely joining the group, they were asked to rate the agent's politeness according to four distinct aspects (Clarity, Face loss, Positive face, and Negative face). Across all strategies, in 48% of the trials participants were successfully persuaded to join the group at an inconvenient location. Out of those trials, participants adhered to social conventions by not crossing the convex empty space between the group members (o-space) in 75% of them on average. Additionally, analysis of verbal and nonverbal behaviors in ECAs shows that direct request strategies are more effective than indirect ones, although in some cases they may be perceived as less polite.

Place, publisher, year, edition, pages
New York,NY,USA: Association for Computing Machinery (ACM), 2022.
Keywords [en]
politeness theory, persuasiveness, virtual reality, small group behavior, embodied conversational agents
National Category
Other Engineering and Technologies Human Computer Interaction
Identifiers
URN: urn:nbn:se:kth:diva-343214DOI: 10.1145/3514197.3549676ISI: 001118873500014Scopus ID: 2-s2.0-85138671810OAI: oai:DiVA.org:kth-343214DiVA, id: diva2:1836343
Conference
IVA '22: ACM International Conference on Intelligent Virtual Agents, Faro, Portugal, September 6 - 9, 2022
Note

Part of ISBN 978-1-4503-9248-8

QC 20240209

Available from: 2024-02-08 Created: 2024-02-08 Last updated: 2025-02-18Bibliographically approved
In thesis
1. Embodying Politeness in Persuasive Humanoid Agents for Small Group Scenarios
Open this publication in new window or tab >>Embodying Politeness in Persuasive Humanoid Agents for Small Group Scenarios
2024 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

In both physical and virtual environments, small group interactions significantly shape our social experiences. Understanding and replicating situated group interactions with virtual agents or physical robots pose possibilities and challenges. Central to these challenges lies the critical aspect of politeness, which serves as a fundamental cornerstone in shaping our social interactions. This PhD thesis investigates the profound significance of politeness strategies in shaping social interactions within small free-standing conversational groups in physical and virtual environments with humanoid artificial agents. It particularly focuses on their adaptability to virtual characters or Embodied Conversational Agents (ECAs) and Human-Robot Interaction (HRI). The thesis explores the impact of these strategies on persuasiveness, adherence to social norms, and the formation of positive perceptions during interactions between participants and virtual agents or humanoid robots while joining a group of artificial humanoid agents. It involves a series of user studies with an experimental setup, which entails presenting participants with dilemmas in either a virtual or physical environment. Participants should decide between expending more effort to comply with the agent’s request or opting for a least-effort alternative to join a group while ignoring the request. Additionally, the setup evaluates participant responses to various politeness strategies expressed by virtual agents or robots when extending invitations to join a small, free-standing group. The research contributes by defining behaviors aligned with politeness strategies, revealing participant adherence to social norms even in situations requiring more effortful choices, and pinpointing optimal behaviors based on criteria such as persuasiveness, politeness, and social adherence. Ultimately, the findings provide insights into the indispensable role of politeness strategies in Human-Agent Interaction to gently influence the decisions of humans while maintaining positive relations with them. These insights pave the way for designing more effective and socially acceptable behaviors for virtual agents and robots across diverse domains.

Abstract [sv]

I både fysiska och virtuella miljöer formar små gruppinteraktioner avsevärt våra sociala upplevelser. Att förstå och replikera sammanhangsbaserade gruppinteraktioner med virtuella agenter eller fysiska robotar innebär möjligheter och utmaningar. Centralt för dessa utmaningar är den kritiska aspekten andående artighet, som fungerar som en grundläggande hörnsten i att forma våra sociala interaktioner. Denna doktorsavhandling undersöker den djupa betydelsen av artighetsstrategier för att forma sociala interaktioner inom små fristående samtalsgrupper i fysiska och virtuella miljöer med humanoida artificiella agenter. Den fokuserar särskilt på deras anpassningsförmåga till virtuella karaktärer eller Embodied Conversational Agents (ECA) och Human-Robot Interaction (HRI). Avhandlingen undersöker effekten av dessa strategier på övertalningsförmåga, efterlevnad av sociala normer och bildandet av positiva uppfattningar under interaktioner mellan deltagare och virtuella agenter eller humanoida robotar samtidigt som de ansluter till en grupp artificiella humanoida agenter. Den består av en serie användarstudier med experimentupplägg, vilket innebär att deltagarna ställs inför dilemman i antingen en virtuell eller fysisk miljö. Deltagarna får välja mellan att lägga ner mer ansträngning på att följa agentens begäran eller välja ett minst ansträngningsalternativ för att ansluta till en grupp samtidigt som de ignorerar begäran. Dessutom utvärderar experimentet deltagarnas svar på olika artighetsstrategier som uttrycks av virtuella agenter eller robotar när de inbjuder till att ansluta till en små, fristående grupp. Forskningen bidrar genom att definiera beteenden i linje med artighetsstrategier, avslöja deltagarnas efterlevnad av sociala normer även i situationer som kräver mer ansträngande val, och fastställa optimala beteenden baserat på kriterier som övertalningsförmåga, artighet och social efterlevnad. Slutligen ger resultaten insikter i den oumbärliga rollen av artighetsstrategier i interaktion mellan människa och agent för att varsamt påverka människors beslut samtidigt som de bibehåller positiva relationer med dem. Dessa insikter banar väg för att utforma mer effektiva och socialt acceptabla beteenden för virtuella agenter och robotar över olika domäner.

Place, publisher, year, edition, pages
Stockholm, Sweden: KTH Royal Institute of Technology, 2024. p. 59
Series
TRITA-EECS-AVL ; 2024:14
Keywords
politeness, persuasiveness, small free-standing conversational groups, embodiment, embodied conversational agents, humanoid robots, virtual reality, immersiveness, human-agent interaction, social norms, multimodal expressive communication, artighet, övertalningsförmåga, små fristående samtalsgrupper, förkroppsligande, förkroppsligade samtalsagenter, humanoida robotar, virtuell verklighet, uppslukande, interaktion mellan människa och agent, sociala normer, multimodal uttrycksfull kommunikation
National Category
Human Computer Interaction Computer and Information Sciences Robotics and automation
Identifiers
urn:nbn:se:kth:diva-343332 (URN)978-91-8040-833-2 (ISBN)
Public defence
2024-03-06, https://kth-se.zoom.us/j/62065064122, Visualization Studio VIC, Lindstedtsvägen 7, Stockholm, 10:00 (English)
Opponent
Supervisors
Note

QC 20240212

Available from: 2024-02-12 Created: 2024-02-09 Last updated: 2025-02-18Bibliographically approved

Open Access in DiVA

fulltext(1004 kB)99 downloads
File information
File name FULLTEXT01.pdfFile size 1004 kBChecksum SHA-512
3359c5b5cd6626430c100ad04f2ef1c47c9708613ad17d1e82659eeb0bb31f239d0faf9579fbca117b3d81a4181b6eb0e5f0362a6a7b291e6be3f27aee814c49
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Iop, AlessandroZojaji, SahbaPeters, Christopher

Search in DiVA

By author/editor
Iop, AlessandroZojaji, SahbaPeters, Christopher
By organisation
Computational Science and Technology (CST)
Other Engineering and TechnologiesHuman Computer Interaction

Search outside of DiVA

GoogleGoogle Scholar
Total: 99 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 262 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf