🤖 AI Summary
This study investigates the dynamic mechanisms of emotional alignment, semantic exploration, and linguistic innovation in human–AI collaborative storytelling. Method: Leveraging a museum-based public installation, we orchestrated iterative co-creation of 27 narratives between over 3,000 visitors and a large language model (LLM), enabling the first real-world quantification of their differential roles in narrative generation. We developed a binary interaction analytical framework integrating sentiment analysis, Sentence-BERT semantic embeddings, information entropy, and resonance metrics. Contribution/Results: Empirical findings demonstrate that human participation significantly enhances semantic diversity and narrative novelty—effects nearly absent in AI-only control conditions. This confirms the irreplaceable role of human input in steering creative direction and fostering conceptual divergence. The study establishes a new paradigm of human–AI creativity: “human-driven semantic innovation, AI-enabled emotional coordination.”
📝 Abstract
Human-AI interactions are increasingly part of everyday life, yet the interpersonal dynamics that unfold during such exchanges remain underexplored. This study investigates how emotional alignment, semantic exploration, and linguistic innovation emerge within a collaborative storytelling paradigm that paired human participants with a large language model (LLM) in a turn-taking setup. Over nine days, more than 3,000 museum visitors contributed to 27 evolving narratives, co-authored with an LLM in a naturalistic, public installation. To isolate the dynamics specific to human involvement, we compared the resulting dataset with a simulated baseline where two LLMs completed the same task. Using sentiment analysis, semantic embeddings, and information-theoretic measures of novelty and resonance, we trace how humans and models co-construct stories over time. Our results reveal that affective alignment is primarily driven by the model, with limited mutual convergence in human-AI interaction. At the same time, human participants explored a broader semantic space and introduced more novel, narratively influential contributions. These patterns were significantly reduced in the simulated AI-AI condition. Together, these findings highlight the unique role of human input in shaping narrative direction and creative divergence in co-authored texts. The methods developed here provide a scalable framework for analysing dyadic interaction and offer a new lens on creativity, emotional dynamics, and semantic coordination in human-AI collaboration.