Abstract
Storytelling has accompanied mankind since its beginnings and receiving stories is still a popular leisure activity. Today, new storytelling media are emerging. For example, social robots can act as storytellers, using different modalities such as facial expressions or body postures. With the goal of automating robotic storytelling, we annotated stories with emotion labels which a robot can use to automatically adapt its behavior to. Doing so, three different approaches and a baseline are compared in two studies in this paper: 1) manual labels by human annotators (MA), 2) software-based word-sensitive annotation using the Linguistic Inquiry and Word Count program (LIWC), 3) a LLM approach using ChatGPT (GPT), and 4) random annotations as baseline (RBL). In an online study showing videos of a storytelling robot, the annotations were validated using a backwards annotation task, with GPT closely followed by MA achieving the best, and the RBL the worst results. In a subsequent lab user study, all versions of the story were compared regarding storytelling experience, emotions, and robot perception, revealing no significant differences for any of these variables based on the annotation approach, but a significant decrease of negative affect and fatigue over the storytelling in all conditions. Taken together, the results indicate suitability of both the manual and GPT approaches. On this empirical basis, the Automatic Robotic Storyteller was implemented using GPT-based annotations and bodily expressions. The reduced programming effort of our system makes robotic storytelling accessible to a broader audience, strengthening its deployment in the field of affective computing.