Skip to main content
QUICK REVIEW

[Paper Review] PuppetChat: Fostering Intimate Communication through Bidirectional Actions and Micronarratives

Emma Jiren Wang, Siying Hu|arXiv (Cornell University)|Feb 23, 2026
Digital Mental Health Interventions0 citations
TL;DR

PuppetChat presents a dyadic messaging prototype that uses reciprocity-aware action recommendations and personalized micronarratives to deepen intimate communication, evaluated in a 10-day field study with 11 dyads.

ABSTRACT

As a primary channel for sustaining modern intimate relationships, instant messaging facilitates frequent connection across distances. However, today's tools often dilute care; they favor single tap reactions and vague emojis that do not support two way action responses, do not preserve the feeling that the exchange keeps going without breaking, and are weakly tied to who we are and what we share. To address this challenge, we present PuppetChat, a dyadic messaging prototype that restores this expressive depth through embodied interaction. PuppetChat uses a reciprocity aware recommender to encourage responsive actions and generates personalized micronarratives from user stories to ground interactions in personal history. Our 10-day field study with 11 dyads of close partners or friends revealed that this approach enhanced social presence, supported more expressive self disclosure, and sustained continuity and shared memories.

Motivation & Objective

  • Motivate a shift from one-way reactions to reciprocal, action-based exchanges in intimate messaging.
  • Ground interactions in personal history by anchoring actions to editable micronarratives drawn from user stories.
  • Enable user control over narrative generation and action recommendations to preserve agency.
  • Create lightweight, revisitable traces of interactions to build a shared memory timeline.

Proposed method

  • Develop PuppetChat, a real-time one-to-one messaging prototype with an action library of 42 expressive gestures and a micronarrative generator anchored in user stories.
  • Use a reciprocity-aware recommender to suggest four contextually relevant actions for each message.
  • Generate editable micronarratives tied to actions to ground expressions in personal narratives.
  • Provide an interface with avatar actions, an action recommendation button, and a replayable interaction history.
  • Conduct a 10-day field study with 11 dyads to evaluate impact on social presence, self-disclosure, continuity, and shared memories.

Experimental results

Research questions

  • RQ1Does reciprocal action exchange increase perceived social presence in mediated intimate communication?
  • RQ2Do micronarratives anchored in personal stories improve expressivity and context in dyadic messaging?
  • RQ3Can the combination of bidirectional actions and editable narratives sustain interaction continuity and shared memories over time?
  • RQ4What design mechanisms (reciprocity, personalization, memory) most effectively enhance relatedness in long-distance or dyadic IM?

Key findings

  • Reciprocal actions reliably increased social presence and a sense of co-performance in a non-immersive text-based interface.
  • Action–micronarrative pairs promoted sequences of interaction, sustaining flow and avoiding breaks in conversation.
  • Editable micronarratives enabled precise yet face-saving self-disclosure and supported playful co-construction of meaning.
  • Accumulated actions and captions created revisitable traces that supported reflection on shared moments and memories.

Better researchstarts right now

From reading papers to final review, dramatically reduce your research time.

No credit card · Free plan available

This review was created by AI and reviewed by human editors.