We present in this paper a detailed comparison of different algorithms and devices to determine the number of words read in everyday life. We call our system the “Wordometer”. We used three kinds of eye tracking systems in our experiment: mobile video-oculography (MVoG); stationary video-oculography (SVoG); and electro-oculography (EoG). By analyzing the movement of the eyes we were able to estimate the number of words that a user read. Recently, inexpensive eye trackers have appeared on the market. Thus, we undertook a large-scale experiment that compared three devices that can be used for daily reading on a screen: the Tobii Eye X SVoG; the JINS MEME EoG; and the Pupil MVoG. We found that the accuracy of the everyday life devices and professional devices was similar when used with the Wordometer. We analyzed the robustness of the systems for special reading behaviors: rereading and skipping.
With the MVoG, SVoG and EoG systems, we obtained estimation errors respectively, 7.2%, 13.0%, and 10.6% in our main experiment. In all our experiments, we obtained 300 recordings by 14 participants, which amounted to 109,097 read words.
The eye tracking technology is used for four decades for studying reading behavior. The applications are various: estimating the reader comprehension, identifying the reader, summarizing a read document, creating a reading-life log, etc. The gaze data used in such applications has to be accurate enough to perform the analysis. In order to improve the accuracy, most of the experiments are set up with restrictive conditions such as using a head fixation and a professional eye tracker. It implies that the results are valid only in restrictive laboratory settings and an unrealistic small error is produced by the experiment. However, the use of affordable eye trackers in realistic conditions of reading leads to large errors in the recordings. We propose a new algorithm to correct the vertical error and to align the gazes with the text. The proposed algorithm is robust to rereading and skipping some parts of text, contrary to all the other algorithms of the state of the art. We show that up to 69 % of the gazes are aligned with the correct text lines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.