Training an EOG-based wordometer without reading - a simple HCI application to quantify reading metrics

Abstract

Reading is the activity through which humans decipher written symbols in an effort to extract information from written text. Whether written on paper, or displayed on a screen, literacy can be considered as a valuable tool to one’s social and educational development. Through the use of electrooculography (EOG), as a means of tracking one’s eye movements, this work presents the development of a novel Wordometer application, capable of measuring the quantity of reading. Through the incorporation of a novel light-weight cue-based training protocol, this application obtained an average word estimation error of 8.23% when tested across five human subjects using EOG data.