Intent Recognition in Collaborative Interfaces

Collaboration consists of the joint activities of several participants. In order for joint activities to advance, participants must effectively coordinate their actions, and effective coordination appeals to common ground. [4,5] In this paper, we discuss an intent recognition technique that utilizes information that is part of common ground – namely, shared references to domain objects and their associated information. Our technique is designed to support an adaptive information management system for the Vesselworld collaborative system. The two key insights which motivate this work are: 1) C o o r d i n a t i n g representations [2] may be introduced to groupware systems which structure shared information and facilitate coordination, and 2) AI techniques can be employed to take advantage of such structured information to support effective interface adaptations. Here, we introduce a technique for intent recognition that uses information from a coordinating representation designed to support common ground.