Virtual assistant: an artificial agent for enhancing content acquisition: how ambient media elicit information from humans

In this paper, we propose a novel framework "Virtual Assistant" for enhancing content potentially procured by ambient media. The Virtual Assistant is an artificial agent simulating a human assistant shown in TV programs and prompts users to provide feedback by asking questions or back-channeling. This framework ensures that sufficient information is provided in the captured content while users interact in a natural and enjoyable way with the agent. We developed a prototype agent based on a chatbot-like approach and applied it to a daily cooking scene. The experimental results demonstrate a good potential of the Virtual Assistant framework, allowing a person to provide feedback easily with few interruptions, lifting the face towards the camera, and eliciting a variety of useful information.