Supervising attention in an e-learning system

Abstract

Until now, the level of attention of a worker has been evaluated through his/her productivity: the more one produces, the better his/her attention at work. First, the worst aspect about this approach is that it only points out a potential decrease of attention after a productivity loss. An approach that could point out, in advance, upcoming breaks in attention could allow active/preventive interventions rather than reactive ones. In this paper we present a distributed system for monitoring attention in teams (of people). It is especially suited for people working with computers and it can be interesting for domains such as the workplace or the classroom. It constantly analyzes the behavior of the user while interacting with the computer and together with knowledge about the task, is able to temporally classify attention.