I Know What You Don't Know: Proactive Learning through Targeted Human Interaction

Humans communicate extensively through "meta-information" encoded in emitted non-verbal signals. This meta-information not only allows us to analyze an individual's external emotional state but also certain internal states. For example, humans are able to learn from others thanks to their ability to determine their most knowledgeable peers in a given domain through their interactions with these individuals. As autonomous agents expand into more socially oriented tasks, they must capture and reason through these emitted cues to better understand their human counterparts. In this work, we conduct two experiments. First, we train a model to predict the knowledgeability of speakers using non-verbal features. Next we simulate the process of selecting the most knowledgeable person in a given domain using a proactive learning approach. The results indicate our agent is capable of observing human behavior and using this information to select a specific human for aid on a given question.