In this paper, we explored the use of features that represent body posture and movement for automatically detecting people's emotions in non-acted standing scenarios. We focused on four emotions that are often observed when people are playing video games: triumph, frustration, defeat, and concentration. The dataset consists of recordings of the rotation angles of the player's joints while playing Wii sports games. We applied various machine learning techniques and bagged them for prediction. When body pose and movement features are used we can reach an overall accuracy of 66.5% for differentiating between these four emotions. In contrast, when using the raw joint rotations, limb rotation movement, or posture features alone, we were only able to achieve accuracy rates of 59%, 61%, and 62% respectively. Our results suggest that features representing changes in body posture can yield improved classification rates over using static postures or joint information alone.

No abstract

A storyteller builds a narrative that captivates the audience, immersing them in the story. Storytelling is an interactive process. Though the listeners cannot affect what happens in the story, a good narrator observes the audience's responses and adjusts his/her storytelling accordingly. We present an automated storytelling agent that is aimed at achieving the same effect. While presenting a story, the user is given chances to give comments or ask questions. The agent estimates the user's preferences towards various topics from these responses and weighs the factors of novelty, current interest, and consistency for generating the next part of the narration. We describe the components of the agent, and an example of applying it for narrating a Chinese fantasy story.

No abstract

Storytelling, when happening face to face, is a highly interactive process. A good storyteller attracts the audience by continuously observing their responses and adjusting the storytelling accordingly. The goal of this project is to simulate this process in digital storytellers. We created an automatic storytelling system that periodically estimates the user’s preferences and adapts the content in the subsequent storytelling by balancing novelty and topic consistency. We have performed an empirical evaluation on the effectiveness of our approach. The results indicate that gender and age play important roles in affecting one’s subjective experience. For younger subjects, stories with mixed amount of novelty and topic consistency are more preferred while for older subjects, larger amounts of variation are preferred. Additionally, in general, women enjoyed the stories more than men.