More-than-Human Storytelling: Designing Longitudinal Narrative Engagements with Generative AI

TL;DR

This study investigates long-term interactions with generative AI storytelling agents through a two-week diary study, revealing complex user-AI dynamics, benefits, and challenges in sustained narrative engagement.

Contribution

It provides initial empirical insights and design considerations for creating adaptive, more-than-human storytelling systems using generative AI.

Findings

Users appreciated personal notes and reflection opportunities.

Limitations in narrative coherence caused frustration.

Long-term engagement reveals complex user-AI relationship dynamics.

Abstract

Longitudinal engagement with generative AI (GenAI) storytelling agents is a timely but less charted domain. We explored multi-generational experiences with "Dreamsmithy," a daily dream-crafting app, where participants (N = 28) co-created stories with AI narrator "Makoto" every day. Reflections and interactions were captured through a two-week diary study. Reflexive thematic analysis revealed themes likes "oscillating ambivalence" and "socio-chronological bonding," highlighting the complex dynamics that emerged between individuals and the AI narrator over time. Findings suggest that while people appreciated the personal notes, opportunities for reflection, and AI creativity, limitations in narrative coherence and control occasionally caused frustration. The results underscore the potential of GenAI for longitudinal storytelling, but also raise critical questions about user agency and ethics. We contribute initial empirical insights and design considerations for developing adaptive, more-than-human storytelling systems.