Wrapped in Anansi's Web: Unweaving the Impacts of Generative-AI Personalization and VR Immersion in Oral Storytelling

TL;DR

The paper tackles preserving and revitalizing oral storytelling by combining VR immersion with Gen-AI-driven personalization in a culturally significant Akan folktale (Anansi the Spider). Using a $2 \times 2$ between-subjects mixed-methods design with $n=48$, it demonstrates that VR enhances engagement and cultural learning, while personalization deepens immersion and reflection, particularly when interacting with AI-driven NPCs. The findings support cultural preservation, cross-cultural inclusion, and meaningful self-reflection, offering actionable design guidelines for balancing authenticity with interactive storytelling. The work highlights both the promise of immersive, co-created folklore in the digital age and the need for careful evaluation and collaboration with communities to maintain cultural integrity and impact.

Abstract

Oral traditions, vital to cultural identity, are losing relevance among youth due to the dominance of modern media. This study addresses the revitalization of these traditions by reconnecting young people with folklore. We introduce Anansi the Spider VR, a novel virtual space that combines first-person virtual reality (VR) with generative artificial intelligence (Gen-AI)-driven narrative personalization. This space immerses users in the Anansi Spider story, empowering them to influence the narrative as they envision themselves as the `protagonists,' thereby enhancing personal reflection. In a 2 by 2 between-subjects study with 48 participants, we employed a mixed-method approach to measure user engagement and changes in interest, complemented by semi-structured interviews providing qualitative insights into personalization and immersion. Our results indicate that personalization in VR significantly boosts engagement and cultural learning interest. We recommend that future studies using VR and Gen-AI to revitalize oral storytelling prioritize respecting cultural integrity and honoring original storytellers and communities.

Figures (17)

• Figure 1: Experimental setup for VR and Non-VR conditions.
• Figure 2: Interactive Narrative Path in 'Anansi the Spider VR': Figure illustrates the five key stages of the VR narrative. Participants start their journey at Stage 1 in the village, walking along a jungle path to Stage 2 where they meet Anansi, climb Anansi's web at Stage 3 to receive tasks from the Sky God, search for Onini at Stage 4, and conclude the experience at Stage 5.
• Figure 3: Interaction with Onini in the VR environment, where participants use Speech-to-Text options to persuade Onini to stretch alongside a bamboo stick, as part of their task in the 'Anansi the Spider VR' narrative.
• Figure 4: System Architecture of the Player NPC Interaction Model. Player speech is converted into text by OpenAI’s Whisper system, and GPT-4 generates dynamic narrative responses for the NPC Onini. The orange arrows represent the communication between Whisper, GPT-4, and ElevenLabs, where player input is processed, and responses are generated and converted back into speech. ElevenLabs handles both dynamically generated and pre-scripted text-to-speech outputs for all NPCs.
• Figure 5: User Engagement Scores Comparing Different Conditions Between NVNP, NVP, VNP, and VP. *, **, ***, and **** correspond to significance levels of $p < .05$, $p < .01$, $p < .001$, and $p < .0001$, respectively. Response options used a Likert scale ranging from 1 (Strongly disagree) to 5 (Strongly agree).