Table of Contents
Fetching ...

Metamorpheus: Interactive, Affective, and Creative Dream Narration Through Metaphorical Visual Storytelling

Qian Wan, Xin Feng, Yining Bei, Zhiqi Gao, Zhicong Lu

TL;DR

Metamorpheus addresses the lack of accessible tools for affective dream narration by integrating AI-assisted metaphor generation with visual storytelling to support meaning-making and mindfulness. The system enables co-creative narration where users and generative AI produce metaphorical images and text anchored to dream emotions, organized on a storyline with color-filter customization. In a phenomenological lab study with 12 participants, the approach yielded vivid recall, meaningful reflection, and a sense of connectedness, while preserving user agency and offering a non-threatening avenue for sharing personal experiences. The work contributes a concrete design and evaluation of an affective interface that leverages generative AI for meaning co-construction, with implications for psychotherapy support and personal informatics beyond dream tracking.

Abstract

Human emotions are essentially molded by lived experiences, from which we construct personalised meaning. The engagement in such meaning-making process has been practiced as an intervention in various psychotherapies to promote wellness. Nevertheless, to support recollecting and recounting lived experiences in everyday life remains under explored in HCI. It also remains unknown how technologies such as generative AI models can facilitate the meaning making process, and ultimately support affective mindfulness. In this paper we present Metamorpheus, an affective interface that engages users in a creative visual storytelling of emotional experiences during dreams. Metamorpheus arranges the storyline based on a dream's emotional arc, and provokes self-reflection through the creation of metaphorical images and text depictions. The system provides metaphor suggestions, and generates visual metaphors and text depictions using generative AI models, while users can apply generations to recolour and re-arrange the interface to be visually affective. Our experience-centred evaluation manifests that, by interacting with Metamorpheus, users can recall their dreams in vivid detail, through which they relive and reflect upon their experiences in a meaningful way.

Metamorpheus: Interactive, Affective, and Creative Dream Narration Through Metaphorical Visual Storytelling

TL;DR

Metamorpheus addresses the lack of accessible tools for affective dream narration by integrating AI-assisted metaphor generation with visual storytelling to support meaning-making and mindfulness. The system enables co-creative narration where users and generative AI produce metaphorical images and text anchored to dream emotions, organized on a storyline with color-filter customization. In a phenomenological lab study with 12 participants, the approach yielded vivid recall, meaningful reflection, and a sense of connectedness, while preserving user agency and offering a non-threatening avenue for sharing personal experiences. The work contributes a concrete design and evaluation of an affective interface that leverages generative AI for meaning co-construction, with implications for psychotherapy support and personal informatics beyond dream tracking.

Abstract

Human emotions are essentially molded by lived experiences, from which we construct personalised meaning. The engagement in such meaning-making process has been practiced as an intervention in various psychotherapies to promote wellness. Nevertheless, to support recollecting and recounting lived experiences in everyday life remains under explored in HCI. It also remains unknown how technologies such as generative AI models can facilitate the meaning making process, and ultimately support affective mindfulness. In this paper we present Metamorpheus, an affective interface that engages users in a creative visual storytelling of emotional experiences during dreams. Metamorpheus arranges the storyline based on a dream's emotional arc, and provokes self-reflection through the creation of metaphorical images and text depictions. The system provides metaphor suggestions, and generates visual metaphors and text depictions using generative AI models, while users can apply generations to recolour and re-arrange the interface to be visually affective. Our experience-centred evaluation manifests that, by interacting with Metamorpheus, users can recall their dreams in vivid detail, through which they relive and reflect upon their experiences in a meaningful way.
Paper Structure (35 sections, 6 figures, 2 tables)

This paper contains 35 sections, 6 figures, 2 tables.

Figures (6)

  • Figure 1: The storyline visualisation on the interface arranges the dream narrative in a linear order. Each metaphorical scene is represented as an anchor point on a horizontal axis. The current generated images dangle from the anchor points, and previous generations are preserved above. Users can click on previous generations to switch it into display.
  • Figure 2: The metaphor editing process.
  • Figure 3: Scene I: Exciting Old crush holding my hands - Electric sparks
  • Figure 4: Scene II: Thrilling but a bit worrying Hugging and kissing - Embracing Flames
  • Figure 6: Two different shapes for literal and metaphorical scenes.
  • ...and 1 more figures