作者: Georg Buscher , Andreas Dengel , Ralf Biedert , Ludger V. Elst
关键词: Eye movement 、 Reading (process) 、 Eye tracking 、 Information retrieval 、 Relevance (information retrieval) 、 Computer science 、 Quality (business) 、 Relation (database) 、 Personalization 、 Relevance feedback
摘要: Reading is one of the most frequent activities knowledge workers. Eye tracking can provide information on what document parts users read, and how they were read. This article aims at generating implicit relevance feedback from eye movements that be used for retrieval personalization further applications.We report findings two studies which examine relation between several movement measures user-perceived read text passages. The results show are generally noisy, but after personalizing them we find clear relations relevance. In addition, second study demonstrates effect using reading behavior as search. indicate gaze-based very useful greatly improve quality Web concludes with an outlook introducing attentive documents keeping track consume them. Based feedback, describe a number possible applications to make working more effective.