A System for Multimodal Exploration of Social Spaces

摘要

This paper describes a system developed to help people explore local communities by providing navigation services in social spaces created by members of the communities. Just as a community's social space is formed by communication and knowledge-sharing practices, the proposed system utilizes data of the corresponding social network to reconstruct the social space, which is otherwise not physically perceptible but imaginary and yet experiential and learnable. The social space is modeled with an agent network, where each agent stands for a member of the community and has knowledge about expertise and personal characteristics of other members. An agent can gather information, using its social "connections," to find community members most suitable to communicate to in a specific situation defined by the system's user. The system then deploys its multimodal interface, which operates with 3D graphics and haptic virtual environments and "maps" the social space onto a representation of the relevant physical space, to advise the user on an efficient communication strategy for the given community. A prototype of the system is built and used in a pilot study. The study results are briefly discussed, conclusions are drawn, and implications for future work are formulated.