The role of extraversion in AI-mediated communication: user personality and AI trait preferences in Chinese dyads

Wang, Jindi, Ivrissimtzis, Ioannis, Li, Zhaoxing, Gu, Wen and Shi, Lei (2025) The role of extraversion in AI-mediated communication: user personality and AI trait preferences in Chinese dyads. 20th IFIP TC13 International Conference on Human-Computer Interaction, Belo Horizonte, Minas Gerais, Brazil. 09 - 12 Sep 2025. 5 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

As AI chat assistants become integral to textual communication, understanding user preferences for conversational style is crucial. This user study of 28 people participating in AI-assisted icebreaking conversations in Chinese, explores the effects of AI extraversion levels (Extraverted, Average, Introverted) and linguistic styles (Humorous, Respectful) on user experience. The results reveal a general preference for Extraverted AI—especially among introverted users—and for natural style-personality pairings (Extraverted-Humorous, Introverted-Respectful). These findings highlight the importance of aligning AI personality and language style with user expectations to enhance interaction quality.

Text

camera_ready__INTERACT2025 - Accepted Manuscript

Restricted to Repository staff only

Request a copy