Automatic gaze-based user-independent detection of mind wandering during computerized reading

Abstract

Mind wandering is a ubiquitous phenomenon where attention involuntarily shifts from task-related thoughts to internal task-unrelated thoughts. Mind wandering can have negative effects on performance; hence, intelligent interfaces that detect mind wandering can improve performance by intervening and restoring attention to the current task. We investigated the use of eye gaze and contextual cues to automatically detect mind wandering during reading with a computer interface. Participants were pseudorandomly probed to report mind wandering while an eye tracker recorded their gaze during the reading task. Supervised machine learning techniques detected positive responses to mind wandering probes from eye gaze and context features in a userindependent fashion. Mind wandering was detected with an accuracy of 72 % (expected accuracy by chance was 60 %) when probed at the end of a page and an accuracy of 67 % (chance was 59 %) when probed in the midst of reading a page. Global gaze features (gaze patterns independent of content, such as fixation durations) were more effective than content-specific local gaze features. An analysis of the features revealed diagnostic patterns of eye gaze behavior during mind wandering: (1) certain types of fixations were longer; (2) reading times were longer than expected; (3) more words were skipped; and (4) there was a larger variability in pupil diameter. Finally, the automatically detected mind wandering rate correlated negatively with measures of learning and transfer even after controlling for prior knowledge, thereby providing evidence of predictive validity. Possible improvements to the detector and applications that utilize the detector are discussed.

Observing response processes with eye tracking in international large-scale assessments: evidence from the OECD PIAAC assessment

“…However, the rise of research into 'processes data' in assessment (Ercikan and Pellegrino 2017;Zumbo and Hubley 2017) and advances in eye tracker technology (Bixler and D'Mello 2016;D'Mello et al, 2017) suggest that the application of eye tracking techniques can be extended to observations of how tested populations receive and engage with test items. The contribution of eye tracking in large-scale assessments relates to at least two distinct areas.…”

“…Future eye tracking studies conducted in naturalistic 'in vivo' assessment environments (Maddox and Zumbo 2017) such as classrooms or households may therefore identify behaviours associated with respondent disengagement, 'mind wandering' and associated re-reading (Bixler and D'Mello 2016;Varao-Sousa et al 2017). There is also scope for further research to investigate the impact on behaviour of wearing eye tracking glasses (see Risko and Kingston 2011), and the impact of variations in luminance on the measurement of pupil dilations.…”

Wandering eyes: Eye movements during mind wandering in video lectures

“…For example, the usual association between looking times and word properties (e.g., word frequency) was reduced during MW (Foulsham, Farley, & Kingstone, 2013;Reichle, Reineberg, & Schooler, 2010;Steindorf & Rummel, 2019); readers also tended to skip more words and perform fewer horizontal eye movements during MW (Bixler & D'Mello, 2016;Faber, Bixler, & D'Mello, 2018). These findings not only inspired theoretical accounts of how reading is disrupted during MW (e.g., Smallwood, 2011) but also facilitated the development of algorithms to detect MW during natural reading (e.g., Bixler & D'Mello, 2016;Faber et al, 2018). These successes point to the importance to expand this line of research to various lecture settings to better understand how the learner's attention is disrupted and how we can help learners recover from MW.…”

“…One common measure for examining the when question is fixation duration. Previous studies found that MW was associated with longer mean fixation duration in reading (Bixler & D'Mello, 2016;Foulsham et al, 2013;Reichle et al, 2010) and scene F I G U R E 1 An illustration of the lecture videos used (Study 1 at left, education; and Study 2 at right, genetics). Areas of interest were noted by dotted lines.…”

Predicting students’ attention in the classroom from Kinect facial and body features

“…Video observation and face analysis usually require high-quality image and are applicable to single-person observation, which limits their usability or reduces accuracy and available complexity of image analysis [1] in the classroom setting. Eye tracking devices are very successful in measuring affective parameters such as concentration in the computerized learning environments, and Bixler et al were using eye tracking data detect mind wandering during computerized reading [19]. Apart from visual signals, other types of measurements such as brainwaves (EEG) were utilized to assess attention level of students [12,20].…”