Japanese / English


論文の言語 英語
著者 Olivier Augereau, Clement Jacquet, Koichi Kise, Nicholas Journet
論文名 Vocabulometer: An eye-tracking web platform for reading analysis
論文誌名 Proceedings of the IAPR International Workshop on Document Analysis Systems
年月 2018年4月
要約 The eye-tracking technology reached a new breakthrough since the last years with the development of low-cost eye trackers. The technology is now accessible for many people, which allows to use data mining and learning algorithms to analyze the reading behavior of different readers. However, almost no eye gaze database are available for the research community. We propose a web platform for large scale recordings through a web interface named Vocabulometer. To encourage people to use this platform we provide service linked to reading and learning language such as counting the number of read words, analyzing the comprehension of the reading, predicting the difficult words or recommending text according to the reader skills. For now the interface is compatible with inexpensive eye trackers such as Tobii Eye X and Tobii 4C. In the future, eye-tracking with webcam could be supported.