Abstract
Recent advances in eye-tracking technology afford the possibility to collect rich data on attentional focus in a wide variety of settings outside the lab. However, apart from anecdotal reports, it is not clear how to maximize the validity of these data and prevent data loss from tracking failures. Particularly helpful in developing these techniques would be to describe the prevalence and causes of tracking failures in authentic environments. To meet this goal, we analyzed video records aligned with eye-tracking data collected from screen-mounted eye trackers employed in a middle-school classroom. Our sample includes records from 35 students recorded during multiple eye-tracking sessions. We compared student head position, body posture, attentiveness, and social interactions for time periods associated with successful and unsuccessful eye tracking. Overall, we observed substantial data loss and found that student inattentiveness, movements toward the eye tracker, and head rotations were the most prevalent factors inducing data loss. In addition, we observed a substantial relationship between data loss and apparent low involvement in the learning task. These data suggest that eye-tracking data loss is an important problem and that it can present a threat to validity because it can bias datasets to overrepresent high involvement behaviors. Based on these findings, we present several recommendations for increasing the proportion of usable data and to counter possible biases that data loss may introduce.
Similar content being viewed by others
References
Anderson, D. R. (1985). Online cognitive processing of television. In L. F. Alwitt & A. M. Mitchell (Eds.), Psychological processes and advertising effects: Theory, research, and application (pp. 177–199). Hillsdale.
Bidwell, J., & Fuchs, H. (2011). Classroom analytics: Measuring student engagement with automated gaze Tracking: Technical report. University of North Carolina at Chapel Hill.
Biswas, G., Segedy, J. R., & Bunchongchit, K. (2016). From design to implementation to practice – A learning by teaching system: Betty’s brain. International Journal of Artificial Intelligence in Education, 26(1), 350–364.
Catrysse, L., Gijbels, D., Donche, V., Maeyer, S. D., Lesterhuis, M., & Bossche, P. V. (2018). How are learning strategies reflected in the eyes? Combining results from self-reports and eye-tracking. British Journal of Educational Psychology, 88, 118–137.
Chen, N., & Guastella, A. (2014). Eye tracking during a psychosocial stress simulation: Insights into social anxiety disorder. In M. Horsley, M. Eliot, B. Knight, & R. Reilly (Eds.), Current trends in eye tracking research. Springer.
Colliot, T., & Jamet, É. (2018). Understanding the effects of a teacher video on learning from a multimedia document: An eye-tracking study. Educational Technology Research and Development, 66(6), 1415–1433.
Dalrymple, K. A., Manner, M. D., Harmelink, K. A., Teska, E. P., & Elison, J. T. (2018). An examination of recording accuracy and precision from eye tracking data from toddlerhood to adulthood. Frontiers in Psychology, 9, 803.
Holmqvist, K., Nyström, M., Andersson, R., Dewhurst, R., Jarodzka, H., & van de Weijer, J. (2011). Eye tracking: A comprehensive guide to methods and measures. Oxford University Press.
Holmqvist, K., Nyström, M., & Mulvey, F. (2012). Eye tracker data quality: What it is and how to measure it. Eye Tracking Research and Applications Symposium (ETRA). https://doi.org/10.1145/2168556.2168563
Hutt, S., Mills, C., White, S., Donnelly, P. J., & D'Mello, S. K. (2016). The Eyes Have It: Gaze-Based Detection of Mind Wandering during Learning with an Intelligent Tutoring System. Proceedings of the 9th International Educational Data Mining Society.
Jankovski, C., & Schofield, D. (2017). The eyes have it: Using eye tracking technology to assess the usability of learning management systems in elementary schools. European Journal of Education Studies, 3(10), 425–458. https://doi.org/10.5281/zenodo.1034181
Levin, D. T., & Keliikuli, K. (2020). An empirical assessment of cinematic continuity. Psychology of Aesthetics, Creativity, and the Arts. https://doi.org/10.1037/aca0000344
Miller, B. W. (2015). Using reading times and eye-movements to measure cognitive engagement. Educational Psychologist, 50(1), 31–42. https://doi.org/10.1080/00461520.2015.1004068
Mudrick, N. V., Azevedo, R., & Taub, M. (2019). Integrating metacognitive judgments and eye movements using sequential pattern mining to understand processes underlying multimedia learning. Computers in Human Behavior, 96, 223–234.
Niehorster, D. C., Cornelissen, T. H. W., Holmqvist, K., Hooge, I. T. C., & Hessels, R. S. (2018). What to expect from your remote eye-tracker when participants are unrestrained. Behavior Research Methods, 50(1), 213–222. https://doi.org/10.3758/s13428-017-0863-0
Ooms, K., Dupont, L., Lapon, L., & Popelka, S. (2015). Accuracy and precision of fixation locations recorded with the low-cost Eye Tribe tracker in different experimental set-ups. Journal of Eye Movement Research, 8(1), 1–24. https://doi.org/10.16910/jemr.8.1.5
Rajendran, R., Kumar, A., Carter, K. E., Levin, D. T., & Biswas, G. (2018). Predicting learning by analyzing eye-gaze data of reading behavior [Paper Presentation]. 11th International Conference on Educational Data Mining, Buffalo, NY.
Rayner, K. (1998). Eye movements in reading and information processing: 20 years of research. Psychological Bulletin, 124, 372–422. https://doi.org/10.1037/0033-2909.124.3.372
Rayner, K. (2009). Eye movements and attention in reading, scene perception, and visual search. The Quarterly Journal of Experimental Psychology, 62, 1457–1506. https://doi.org/10.1080/17470210902816461
San Diego, J. P., Aczel, J. C., Hodgson, B. K., & Scanlon, E. (2012). Digital approaches to researching learners’ computer interactions using gazes, actions, utterances and sketches. Educational Technology Research and Development, 60(5), 859–881.
Špakov, O., Istance, H., Hyrskykari, A., Siirtola, H., & Räihä, K. (2019). Improving the performance of eye trackers with limited spatial accuracy and low sampling rates for reading analysis by heuristic fixation-to-word mapping. Behavior Research Methods, 51, 2661–2687. https://doi.org/10.3758/s13428-018-1120-x
Spichtig, A. N., Pascoe, J. P., Ferrara, J. D., & Vorstius, C. (2017). A comparison of eye movement measures across reading efficiency groups in us elementary, middle, and high school students. Journal of Eye Movement Research, 10(4), 5. https://doi.org/10.16910/jemr.10.4.5
Takacs, Z. K., & Bus, A. G. (2016). Benefits of motion in animated storybooks for children’s visual attention and story comprehension an eye-tracking study. Frontiers in Psychology, 7, 1591.
Teicher, M. H., Ito, Y., Glod, C. A., & Barber, N. I. (1996). Objective measurement of hyperactivity and attentional problems in ADHD. Journal of the American Academy of Child & Adolescent Psychiatry, 35(3), 334–342.
van Gog, T., & Jarodzka, H. (2013). Eye tracking as a tool to study and enhance cognitive and metacognitive processes in computer-based learning environments. In R. Azevedo & V. Aleven (Eds.), International handbook of metacognition and learning technologies. Springer international handbooks of education. (Vol. 28). New York: Springer.
Yang, F. Y., Chang, C. Y., Chien, W. R., Chien, Y. T., & Tseng, Y. H. (2013). Tracking learners’ visual attention during a multimedia presentation in a real classroom. Computers & Education, 62, 208–220. https://doi.org/10.1016/j.compedu.2012.10.009
Acknowledgements
The research in this report was supported by NSF grant 1623625 to DTL and GB.
Funding
This paper was supported by grant NSF Grant No. 1623625.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no financial conflicts of interest.
Ethical approval
This paper was supported by grant XXXX, from XXXX. The research involves human participants and it was approved by the Vanderbilt University Institutional Review Board. All participants assented to participate in the research and in addition, parental/guardian consent was obtained. There are no financial conflicts of interest.
Research involving human and animal rights
The research involves human participants and it was approved by the Vanderbilt University Institutional Review Board. All participants assented to participate in the research and in addition, parental/guardian consent was obtained
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix A coding scheme
Social interaction (note: this section only describes participants’ the concrete verbal behaviors not whether they were on-task or off-task).
-
1.
Verbal Talking: Is the student talking? 0 = no 1 = yes (note: if it is not specified, the coding for following other behaviors is aligned with this)
-
2.
Non-verbal Sounds: This refers to the student makes noises. Is the student making non-verbal sounds?
-
3.
Listening: Is the student listening to others?
-
4.
Interacting with Teacher/Research Staff: Is the student talking or listening to Teacher/Research Staff?
-
5.
Interacting with Classmate/Small Group of classmates: Is the student talking or listening to other students?
Task orientation and involvement
-
6.
Off-task—Alone: Is the student, on his/her own, engaging in activities that do not relate to Betty's Brain? For example, the student is performing random movements that do not seem to have a goal, reading other materials, playing, etc.
-
7.
Off-task—Social: Is the student engaging in activities with another student that do not relate to Betty's Brain? For example, the student is interacting with other students, doing things not associated with the Betty's Brain system.
-
8.
Associated Activity—Alone: Is the student associative with others? Talking or listening to other students/teacher/research staff about Betty's Brain without asking or giving instruction. Is the student associative with others?
-
9.
Associated Activity—Social: Talking or listening to other students/teacher/research staff about Betty's Brain without asking or giving instruction.
-
10.
On-task—Alone. Is the student using the Betty's Brain system on his/her own?
-
11.
On-task—Social. Is the student using the Betty's Brain system along with another student or with staff?
-
12.
High: Mostly on-task both two seconds before and after the coding point.
-
13.
Medium: On-task at least at the coding point but off task for some of the two seconds before and/or after the coding point.
-
14.
Low: Mostly off-task both two seconds before and after the coding point.
Head position and camera occlusion
-
15.
Off-screen Look: Is the student looking at anywhere else than the screen?
-
16.
Forward Bending: Is the student forward bending? 0 = no 1 = yes, head 2 = yes, body 3 = yes, both head and body.
-
17.
Backward Bending: Is the student backward bending? The student is leaning back toward the back of the chair.
-
18.
Lateral Bending: Is the student lateral bending?
-
19.
Rotation: Is the student's head rotating to the left or right?
-
20.
Close to Screen: Is the student close to the screen? The full width of the student’s face takes approximately half or more of the width of the video window; the length of the student’s face takes approximately 2/3 or more of the height of the video window (The same computer was used to do the coding and reliability check).
-
21.
Far from Screen: Is the student far from the screen? The student is leaning back, and the shoulder reaches the back of the chair.
-
22.
Eyes-out-of-screen or Occluded: Are the student’s eyes out of the screen? 0 = no 1 = yes, one eye 2 = yes, both eyes
-
23.
Not Present: Is the student not present in the video?
-
24.
Eye Closed: Is the student closing eyes? 0 = no 1 = yes, half-closed/one eye closed 2 = yes, both eyes closed
Other general behaviors
-
25.
Glasses: Is the student wearing glasses?
-
26.
Touch Eye-tracker: Is the student touching the eye-tracker?
-
27.
Move Computer: Is the student moving the eye-tracker?
-
28.
Typing: Is the student typing?
-
29.
Hat or hoodies: Is the student wearing a hat or hoodies?
-
30.
Hands on Face: Are student’s hands on the face? 0 = no 1 = yes, on face 2 = yes, covering some of the eyes 3 = yes, covering the eyes
-
31.
Stand: Is the student standing?
-
32.
Multiple faces: Are there multiple faces in the video?
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xue, X., Xie, S., Mishra, S. et al. A case study of prevalence and causes of eye tracking data loss in a middle school classroom. Education Tech Research Dev 70, 2017–2032 (2022). https://doi.org/10.1007/s11423-022-10154-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11423-022-10154-4