In interactive systems, it is important to keep users' attention and not to get them bored. This paper explains our dialog corpus annotated with boredome information, and reports the analysis results.
We propose a robot behavior generation scheme that generates behaviors based on senses of “curiosity” and “boredom,” to create a companion robot named SELF with which humans do not get bored. The scheme was developed using a simple but unique simulation environment. A red ball and a blue ball were displayed on a computer; the human subject moved the red ball. First, the impressions of various motions and actions of the robot were examined. The actions at moderate speed create agreeable impressions. Based on natural interpersonal interaction patterns, the actions that the robot is expected to generate are classified into four types: “following action,” “fleeing action,” “no interferential action,” and “no action.” We analyzed humans’ impressions of the behaviors of the robot generated by switching the four basic actions at moderate speed. Three types of information transfer efficiency characterized these behaviors. We proposed the behavior generation scheme for SELF. The autonomous learning capability of SELF was realized by updating this conditional probability. Using the developed scheme, SELF can display curiosity and boredom resembling that seen in animals, including humans. Lastly, impressions of the robot behaviors were examined: two were characterized by information transfer efficiency; one was controlled by the proposed scheme.
Self-paced e-learning provides much more freedom in time and locale than traditional education as well as diversity of learning contents and learning media and tools. However, its limitations must not be ignored. Lack of information on learners' states is a serious issue that can lead to severe problems, such as low learning efficiency, motivation loss, and even dropping out of e-learning. We have designed a novel e-learning support system that can visually observe learners' non-verbal behaviors and estimate their learning states and that can be easily integrated into practical e-learning environments. Three pairs of internal states closely related to learning performance, concentration-distraction, difficulty-ease, and interest-boredom, were selected as targets of recognition. In addition, we investigated the practical problem of estimating the learning states of a new learner whose characteristics are not known in advance. Experimental results show the potential of our system.