Quickly Learning User Characteristics for Efficient Interruptability in Agent–User Collaborative Systems

In teamwork when a user and an agent are working together on a joint task it may be important to share information in order to determine the appropriate course of action. However, communication between agents and users can constitute costly user interruptions. One of the most important issue concerning the initiation of information sharing in teamwork is the ability to accurately estimate the cost and benefit arising from those interruptions. While cost estimation of interruptions has been investigated in prior works, all of those works assumed either a large amount of information existed about each user, or only a small number of states needed consideration. This paper presents a novel synthesis between Collaborative Filtering methods together with classification algorithms tools in order to create a fast learning algorithm. This algorithm exploits the similarities between users in order to learn from known users to new but similar users and therefore demands less information on each user. Experimental results indicate the algorithm significantly improves system performance even with a small amount of data on each user.