Poet-Weaver
Table of Contents
About #
Interpersonal communication often involves navigating social challenges like managing expectations and conveying intentions. In practical contexts like productivity and navigation of social boundaries, agent- and AI-mediated communication (AIMC) has served as an effective social intermediary. Communication within personal relationships, especially between intercultural friends from different backgrounds, can also face significant challenges, such as miscommunication and expressive suppression. However, AIMC remains underutilized in the context of established personal relationships due to ethical concerns about agency and authenticity.
We propose designing openly-interpretable AIMC output as an augmented context cue to reduce its active social involvement, balancing AI support with preservation of relational agency. We developed and evaluated Poet-Weaver, a Discord text chat plugin that presents AI-generated insights on user conversations in a stylized, openly-interpretable way to encourage reflection on communication challenges.
Based on users’ chat histories, the AI generates poetic summaries that gently surface subtle emotional dynamics and moments of miscommunication. Rather than providing direct feedback, these stylized and openly-interpretable poems preserve users’ sense of agency and encourage mutual reflection and dialogue.
We conducted a mixed-methods study with 30 intercultural friend pairs to assess Poet-Weaver’s impact. Findings showed Poet-Weaver effectively helped participants address communication failures, although AIMC still influenced users’ behavior even with openly-interpretable output. We recommend future uses of AIMC that support transformative, positive relationship changes while preserving individual responsibility and identity within relationships.
Publications #
- Seraphina Yong, Chi-Lan Yang, Atsushi Hashimoto, Hideaki Kuzuoka, and Shigeo Yoshida. 2025. Poet-Weaver: Reflecting on Communication Failure in Personal Relationships With Stylized AI-Generated Conversation Digests. Proc. ACM Hum.-Comput. Interact. 9, 7, Article CSCW465 (November 2025), 39 pages. https://doi.org/10.1145/3757646