Persode: Personalized Visual Journaling with Episodic Memory-Aware AI Agent

2025-08-28

AI Summary

Traditional text-based reflective journaling fails to meet the emotional expression and engagement needs of Gen Z and Gen Alpha, who strongly prefer visual and immersive interaction modalities. To address this, we propose a personalized visual journaling system integrating a memory-aware conversational agent with automated visual narrative generation. Our approach employs emotion-weighted retrieval-augmented generation (RAG) to dynamically synthesize user-aligned characters, scenes, and artistic styles; further, it leverages user profiling and multimodal prompt engineering to guide text-to-image models in producing high-resonance visual narratives. Empirical evaluation demonstrates significant improvements in young users’ emotional recall fidelity, depth of self-reflection, and long-term engagement—outperforming conventional journaling methods. This work advances digital mental health interventions by introducing a scalable, personalized, next-generation journaling paradigm grounded in affective computing and generative AI.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Reflective journaling often lacks personalization and fails to engage Generation Alpha and Z, who prefer visually immersive and fast-paced interactions over traditional text-heavy methods. Visual storytelling enhances emotional recall and offers an engaging way to process personal expe- riences. Designed with these digital-native generations in mind, this paper introduces Persode, a journaling system that integrates personalized onboarding, memory-aware conversational agents, and automated visual storytelling. Persode captures user demographics and stylistic preferences through a tailored onboarding process, ensuring outputs resonate with individual identities. Using a Retrieval-Augmented Generation (RAG) framework, it prioritizes emotionally significant memories to provide meaningful, context-rich interactions. Additionally, Persode dynamically transforms user experiences into visually engaging narratives by generating prompts for advanced text-to-image models, adapting characters, backgrounds, and styles to user preferences. By addressing the need for personalization, visual engagement, and responsiveness, Persode bridges the gap between traditional journaling and the evolving preferences of Gen Alpha and Z.

Problem

• Addresses lack of personalization in reflective journaling
• Engages digital-native generations with visual storytelling
• Bridges traditional journaling and modern interactive preferences

Innovation

• Personalized onboarding captures user demographics and preferences
• RAG framework prioritizes emotionally significant memories
• Generates prompts for text-to-image visual storytelling