Mirroring the Past: Exploring How Ancestral Digital Self Influences History Learning

2026-08-10

AI Summary

This study addresses the challenge of limited immersion and empathy in history education due to the perceived remoteness of historical content. It proposes “Ancestral Digital Self”—a personalized AI pedagogical agent that integrates learners’ facial features and vocal characteristics to generate avatars situated within historical contexts, thereby enriching the learning experience. This work pioneers the application of personalized AI agents in history education, establishing a reproducible pipeline for AI-generated historical videos and evaluating its impact through educational psychology experiments. Findings indicate that the approach significantly enhances narrative immersion, perceived historical relevance, and self-other merging; however, it does not yield significant gains in immediate knowledge retention and may divert attention from core content due to novelty effects or the uncanny valley phenomenon.

Abstract

Learners often perceive history as distant from themselves, which limits immersion and empathy in history learning. To bridge this gap, we introduce the "Ancestral Digital Self," an AI-generated pedagogical agent presented in prerecorded videos that mirrors the learner's facial features and vocal timbre, representing a historically situated version of the self. We developed a reproducible workflow for creating AI-generated historical learning videos and conducted a within-subjects study (N=36) comparing a Digital Self agent with a non-self pedagogical agent. The Digital Self agent enhanced experiential measures, including narrative transportation, perceived relatedness, self-other inclusion, and agent perception. However, it did not improve immediate learning outcomes: quiz scores were lower in the Digital Self condition, and Remember/Know judgments showed no reliable differences. Interviews further suggested that self-similarity increased familiarity and motivation, while novelty and uncanniness could draw attention away from historical content. These findings offer design implications for future educational environments supported by pedagogical agents.

Problem

• history learning
• learner engagement
• pedagogical agents
• self-relevance
• educational technology

Innovation

• Ancestral Digital Self
• AI-generated pedagogical agent
• self-similarity
• history learning
• narrative transportation