pith. sign in

arxiv: 2512.06834 · v2 · submitted 2025-12-07 · 💻 cs.HC · cs.GR

COIVis: Eye-tracking-based Visual Exploration of Concept Learning in MOOC Videos

Zhiguang Zhou , Ruiqi Yu , Yuming Ma , Hao Ni , Guojun Li , Li Ye , Xiaoying Wang , Yize Li
show 2 more authors
Yigang Wang Yong Wang
This is my paper

Pith reviewed 2026-05-17 00:56 UTC · model grok-4.3

classification 💻 cs.HC cs.GR
keywords eye-trackingMOOCvisual analyticsconcept learninglearner behaviorgaze analysiseducational visualizationvideo exploration
0
0 comments X

The pith

Eye-tracking system maps MOOC video gaze to concept-specific learner states like attention and load.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces COIVis as a visual analytics system that uses eye-tracking to explore how learners process individual concepts during MOOC video lectures. It extracts concepts from video content, aligns them to time and screen regions as Concepts of Interest, and converts gaze paths into sequences that yield five features: Attention, Cognitive Load, Interest, Preference, and Synchronicity. Instructors can then navigate multi-view displays from group summaries down to single-learner paths to spot consistent or anomalous patterns. This approach supplies finer-grained cognitive feedback than click logs or quiz results, which could support more targeted teaching adjustments.

Core claim

COIVis extracts course concepts from multimodal MOOC video content and anchors them to specific spatiotemporal regions as Concepts of Interest. Learners' gaze trajectories are turned into COI sequences, from which five interpretable learner-state features are calculated at the COI level using standard eye-tracking metrics. The resulting narrative multi-view visualization lets instructors move between cohort overviews and individual paths, locate problematic concepts, and compare learning strategies across learners.

What carries the argument

Concepts of Interest (COIs), which anchor abstract course concepts to concrete temporal intervals and screen locations by fusing multimodal video analysis with the lecture's structure.

If this is right

  • Instructors can identify both consistent and anomalous learning patterns across a cohort at the level of individual concepts.
  • Problematic concepts can be located quickly through the visualization rather than inferred from coarse quiz scores.
  • Diverse learner strategies become visible for direct comparison in the same interface.
  • Timely, personalized interventions for struggling learners become feasible based on real-time gaze-derived states.
  • Instructional design can be optimized by revising video segments tied to low-attention or high-load concepts.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The COI alignment technique might transfer to other screen-based instructional videos outside MOOC platforms.
  • Combining the gaze-derived features with clickstream data could produce hybrid models that capture both attention and navigation behavior.
  • Future validation could test whether the five features remain stable when videos are viewed on different devices or at varying playback speeds.

Load-bearing premise

Eye-tracking metrics can be turned into reliable values for the five learner-state features without further validation or controlled experiments.

What would settle it

A controlled test showing that the computed Attention, Cognitive Load, Interest, Preference, and Synchronicity scores for specific COIs do not predict independent measures of learner comprehension or engagement on those same concepts.

Figures

Figures reproduced from arXiv: 2512.06834 by Guojun Li, Hao Ni, Li Ye, Ruiqi Yu, Xiaoying Wang, Yigang Wang, Yize Li, Yong Wang, Yuming Ma, Zhiguang Zhou.

Figure 1
Figure 1. Figure 1: An instructor uses COIVis to explore learners’ performance in the MOOC video Definitions and Terminology of Graphs from a COI (Concept of Interest) perspective. The video and eye tracking data are imported via the Control Panel (a), processed in the backend, and displayed in the Detailed View (c), which shows the instructor’s explanation of each COI along with the original video. The Main View (d) shows al… view at source ↗
Figure 2
Figure 2. Figure 2: Illustration of the COI notion using Concept 1–3 “Relationship [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The pipeline of COIVis consists of three modules: COI definition and eye tracking integration, COI-based learner-state feature analysis, and visual analytics design. thereby anchoring abstract concepts to concrete spatiotemporal positions (R1). The cleaned eye tracking data are then mapped onto these concept positions by assigning fixations that fall within the corresponding concept time window and concept… view at source ↗
Figure 4
Figure 4. Figure 4: Visual design of COIs, relationships, and learner-state features. (a) shows how COIs are linked through four relationships; (b) illustrates how the five [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: (a) and (b) represent alternative designs of COI pathways and learner-state features. (c) shows our final design. [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Four representative learning patterns observed by instructor P3 in [PITH_FULL_IMAGE:figures/full_fig_p012_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Two selected learners are shown in the projection view. Their Attention [PITH_FULL_IMAGE:figures/full_fig_p013_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: The results of Q1-Q8 in our questionnaire. Agree scores to the right, [PITH_FULL_IMAGE:figures/full_fig_p014_8.png] view at source ↗
read the original abstract

Massive Open Online Courses (MOOCs) make high-quality instruction accessible. However, the lack of face-to-face interaction makes it difficult for instructors to obtain feedback on learners' performance and provide more effective instructional guidance. Traditional analytical approaches, such as clickstream logs or quiz scores, capture only coarse-grained learning outcomes and offer limited insight into learners' moment-to-moment cognitive states. In this study, we propose COIVis, an eye tracking-based visual analytics system that supports concept-level exploration of learning processes in MOOC videos. COIVis first extracts course concepts from multimodal video content and aligns them with the temporal structure and screen space of the lecture, defining Concepts of Interest (COIs), which anchor abstract concepts to specific spatiotemporal regions. Learners' gaze trajectories are transformed into COI sequences, and five interpretable learner-state features -- Attention, Cognitive Load, Interest, Preference, and Synchronicity -- are computed at the COI level based on eye tracking metrics. Building on these representations, COIVis provides a narrative, multi-view visualization enabling instructors to move from cohort-level overviews to individual learning paths, quickly locate problematic concepts, and compare diverse learning strategies. We evaluate COIVis through two case studies and in-depth user-feedback interviews. The results demonstrate that COIVis effectively provides instructors with valuable insights into the consistency and anomalies of learners' learning patterns, thereby supporting timely and personalized interventions for learners and optimizing instructional design.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The paper presents COIVis, an eye-tracking-based visual analytics system for concept-level exploration of learning processes in MOOC videos. It extracts course concepts from multimodal content to define Concepts of Interest (COIs) aligned with temporal and spatial structure, transforms gaze trajectories into COI sequences, and computes five learner-state features (Attention, Cognitive Load, Interest, Preference, Synchronicity) at the COI level from eye-tracking metrics. The system offers narrative multi-view visualizations allowing instructors to move from cohort overviews to individual paths, identify problematic concepts, and compare strategies. Evaluation via two case studies and user interviews claims the system yields insights into learning pattern consistency and anomalies to support interventions and instructional design.

Significance. If the feature mappings hold, this work could advance MOOC analytics by moving beyond coarse clickstream or quiz data to fine-grained, concept-anchored cognitive state insights, with the COI anchoring and multi-view narrative design offering a practical framework for instructor support. The integration of eye-tracking with spatiotemporal concept alignment and the progression from aggregate to individual analysis represent a targeted contribution to educational visual analytics. The case studies and interviews provide initial usability evidence, though the absence of quantitative validation limits assessment of impact.

major comments (1)
  1. The section describing computation of the five learner-state features states only that they 'are computed at the COI level based on eye tracking metrics' with no equations, specific metrics (fixation duration, saccade amplitude, pupil dilation, etc.), aggregation rules, thresholds, or validation against self-reports or controlled stimuli. This is load-bearing for the central claim because the visualizations, case-study conclusions about 'consistency and anomalies of learners' learning patterns,' and downstream recommendations for interventions all rest on these features accurately reflecting cognitive states rather than heuristic artifacts.
minor comments (1)
  1. The abstract and evaluation sections would benefit from explicit reference to prior eye-tracking literature used to ground the five features, to clarify how the mappings extend or differ from established metrics.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive and detailed feedback on our manuscript. The major comment identifies an important area for improvement in the description of the learner-state features, which we agree requires expansion to better support the paper's claims. We address this point below and outline the revisions we will make.

read point-by-point responses

  1. Referee: The section describing computation of the five learner-state features states only that they 'are computed at the COI level based on eye tracking metrics' with no equations, specific metrics (fixation duration, saccade amplitude, pupil dilation, etc.), aggregation rules, thresholds, or validation against self-reports or controlled stimuli. This is load-bearing for the central claim because the visualizations, case-study conclusions about 'consistency and anomalies of learners' learning patterns,' and downstream recommendations for interventions all rest on these features accurately reflecting cognitive states rather than heuristic artifacts.

    Authors: We agree that the current manuscript provides only a high-level description of the five learner-state features and lacks the requested computational details, which is a valid concern given their central role. In the revised manuscript, we will add a dedicated subsection detailing the specific eye-tracking metrics for each feature (e.g., fixation duration and count for Attention, pupil dilation and saccade velocity for Cognitive Load, dwell time and regression patterns for Interest and Preference, and temporal alignment metrics for Synchronicity), along with the aggregation rules, formulas, and any thresholds or normalization applied at the COI level. These will be grounded in established eye-tracking literature for inferring cognitive states. We will also explicitly discuss the features' interpretability, potential limitations, and the fact that the evaluation relies on qualitative case studies and user interviews rather than direct quantitative validation against self-reports or controlled stimuli. This addition will strengthen the support for the visualizations and conclusions without altering the paper's scope as a visual analytics contribution. revision: yes

Circularity Check

0 steps flagged

No circularity: system description with external grounding

full rationale

The paper describes a visual analytics system (COIVis) that extracts COIs from MOOC videos, transforms gaze trajectories into sequences, computes five learner-state features from eye-tracking metrics, and supports multi-view visualizations. No equations, fitted parameters, predictions, or derivations appear in the provided text. The central claims rest on case studies, user interviews, and citations to external eye-tracking literature rather than any self-referential loop or input-renamed-as-output. The work is self-contained as a tool-building contribution without load-bearing self-citations or definitional circularity.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

The central claim depends on the domain assumption that standard eye-tracking metrics map meaningfully to the five named cognitive states and on the utility of the introduced COI construct for anchoring concepts in video space and time.

axioms (1)
  • domain assumption Eye-tracking metrics can be mapped to cognitive states such as Attention, Cognitive Load, Interest, Preference, and Synchronicity
    Invoked when transforming gaze trajectories into the five COI-level features.
invented entities (1)
  • Concepts of Interest (COIs) no independent evidence
    purpose: Anchor abstract course concepts to specific spatiotemporal regions in the lecture video
    Defined by aligning extracted concepts with temporal structure and screen space; no independent evidence supplied outside the system itself.

pith-pipeline@v0.9.0 · 5591 in / 1460 out tokens · 102183 ms · 2026-05-17T00:56:31.313894+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

116 extracted references · 116 canonical work pages · 2 internal anchors

  1. [1]

    GPT-4 Technical Report

    J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkat, et al. Gpt-4 technical report.ArXiv Preprint ArXiv:2303.08774, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  2. [2]

    Alemdag and K

    E. Alemdag and K. Cagiltay. A systematic review of eye tracking research on multimedia learning.Computers & Education, 125:413– 428, 2018

    work page 2018

  3. [3]

    M. Ally. Competency profile of the digital and online teacher in future education.International Review of Research in Open and Distributed Learning, 20(2), 2019

    work page 2019

  4. [4]

    Andrienko, N

    G. Andrienko, N. Andrienko, M. Burch, and D. Weiskopf. Visual analytics methodology for eye movement studies.IEEE transactions on Visualization and Computer Graphics, 18(12):2889–2898, 2012

    work page 2012

  5. [5]

    Bachurina and M

    V . Bachurina and M. Arsalidou. Multiple levels of mental attentional demand modulate peak saccade velocity and blink rate.Heliyon, 8(1), 2022

    work page 2022

  6. [6]

    Baker, D

    R. Baker, D. Xu, J. Park, R. Yu, Q. Li, B. Cung, C. Fischer, F. Rodriguez, M. Warschauer, and P. Smyth. The benefits and caveats of using clickstream data to understand student self-regulatory behaviors: opening the black box of learning processes.International Journal of Educational Technology in Higher Education, 17(1):13, 2020

    work page 2020

  7. [7]

    Balasubramanian, S

    V . Balasubramanian, S. G. Doraisamy, and N. K. Kanakarajan. A multimodal approach for extracting content descriptive metadata from lecture videos.Journal of Intelligent Information Systems, 46:121–145,

    work page

  8. [8]

    doi: 10.1007/s10844-015-0356-5

    work page doi:10.1007/s10844-015-0356-5

  9. [9]

    Barria-Pineda, J

    J. Barria-Pineda, J. Guerra, Y . Huang, and P. Brusilovsky. Concept- level knowledge visualization for supporting self-regulated learning. InCompanion Proceedings of the 22nd International Conference on Intelligent User Interfaces, pp. 141–144, 2017

    work page 2017

  10. [10]

    Betaitia, A

    Z. Betaitia, A. Chefrour, and S. Drissi. Exploring Dropout Rates in MOOC Research: A Bibliometric Analysis.Journal of Learning for Development, 12(1):76–92, Mar. 2025. doi: 10.56059/jl4d.v12i1.1597

    work page doi:10.56059/jl4d.v12i1.1597 2025

  11. [11]

    A. M. Borghi. Concepts for which we need others more: The case of abstract concepts.Current Directions in Psychological Science, 31(3):238–246, 2022

    work page 2022

  12. [12]

    B ¨uhler, F

    D. B ¨uhler, F. Hemmert, and J. Hurtienne. Universal and intuitive? scientific guidelines for icon design. InProceedings of Mensch Und Computer 2020, pp. 91–103. 2020

    work page 2020

  13. [13]

    B ¨uhler, F

    D. B ¨uhler, F. Hemmert, J. Hurtienne, and C. Petersen. Design- ing universal and intuitive pictograms (uipp)–a detailed process for more suitable visual representations.International journal of human- computer studies, 163:102816, 2022

    work page 2022

  14. [14]

    Burch, L

    M. Burch, L. L. Chuang, A. Duchowski, D. Weiskopf, and R. Groner. Eye tracking and visualization: introduction to the special thematic issue of the journal of eye movement research.Journal of Eye Movement Research, 10(5):10–16910, 2018

    work page 2018

  15. [15]

    Chen, G.-J

    K.-F. Chen, G.-J. Hwang, and M.-R. A. Chen. Effects of a concept mapping-guided virtual laboratory learning approach on students’ sci- ence process skills and behavioral patterns.Educational Technology Research and Development, 72(3):1623–1651, 2024

    work page 2024

  16. [16]

    Q. Chen, Y . Chen, D. Liu, C. Shi, Y . Wu, and H. Qu. Peakvizor: Visual analytics of peaks in video clickstreams from massive open online courses.IEEE transactions on visualization and computer graphics, 22(10):2315–2330, 2015

    work page 2015

  17. [17]

    Q. Chen, X. Yue, X. Plantaz, Y . Chen, C. Shi, T.-C. Pong, and H. Qu. Viseq: Visual analytics of learning sequence in massive open online courses.IEEE Transactions on Visualization and Computer Graphics, 26(3):1622–1636, 2018. doi: 10.1109/TVCG.2018.2872961

    work page doi:10.1109/tvcg.2018.2872961 2018

  18. [18]

    Chuikova, A

    Z. Chuikova, A. Izmalkova, P. Shirokova, Y . Shtyrov, and A. My- achykov. Eye movement correlates of working memory capacity: Evidence from the reading span task.Psychology, Journal of the Higher School of Economics, 21(3):472–487, 2024. doi: 10.17323/1813-8918 -2024-3-472-487

    work page doi:10.17323/1813-8918 2024

  19. [19]

    Chytry, N

    V . Chytry, N. Mundokova, and M. Kubiatko. Using eye-tracking in education—a review study.Education Sciences, 15(7):853, 2025

    work page 2025

  20. [20]

    Cis ,mas,u, B

    I.-D. Cis ,mas,u, B. R. Cibu, L.-A. Cotfas, and C. Delcea. The Persistence Puzzle: Bibliometric Insights into Dropout in MOOCs.Sustainability, 17(7):2952, Jan. 2025. doi: 10.3390/su17072952

    work page doi:10.3390/su17072952 2025

  21. [21]

    H. C. Cuve, J. Stojanov, X. Roberts-Gaal, C. Catmur, and G. Bird. Validation of gazepoint low-cost eye-tracking and psychophysiology bundle.Behavior Research Methods, 54(2):1027–1049, 2022

    work page 2022

  22. [22]

    Deng and Y

    R. Deng and Y . Gao. A review of eye tracking research on video-based learning.Education and Information Technologies, 28(6):7671–7702,

    work page

  23. [23]

    doi: 10.1007/s10639-022-11486-7 IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, VOL. XX, NO. X, JUNE 20XX 16

    work page doi:10.1007/s10639-022-11486-7

  24. [24]

    L. L. Di Stasi, A. Catena, J. J. Ca ˜nas, S. L. Macknik, and S. Martinez- Conde. Saccadic velocity as an arousal index in naturalistic tasks. Neuroscience & Biobehavioral Reviews, 37(5):968–975, 2013

    work page 2013

  25. [25]

    L. L. Di Stasi, R. Renner, P. Staehr, J. R. Helmert, B. M. Velichkovsky, J. J. Ca ˜nas, A. Catena, and S. Pannasch. Saccadic peak velocity sensitivity to variations in mental workload.Aviation, space, and environmental medicine, 81(4):413–417, 2010

    work page 2010

  26. [26]

    A. T. Duchowski, K. Krejtz, I. Krejtz, C. Biele, A. Niedzielska, P. Kiefer, M. Raubal, and I. Giannopoulos. The index of pupillary activity: Measuring cognitive load vis- `a-vis task difficulty with pupil oscillation. InProceedings of the 2018 CHI conference on human factors in computing systems, pp. 1–13, 2018

    work page 2018

  27. [27]

    El Haddioui

    I. El Haddioui. Eye tracking applications for e-learning purposes: An overview and perspectives.Cognitive Computing in Technology- Enhanced Learning, pp. 151–174, 2019

    work page 2019

  28. [28]

    Evans and I

    T. Evans and I. Jeong. Concept maps as assessment for learning in uni- versity mathematics.Educational Studies in Mathematics, 113(3):475– 498, 2023

    work page 2023

  29. [29]

    J. A. Fredricks, P. C. Blumenfeld, and A. H. Paris. School engagement: Potential of the concept, state of the evidence.Review of educational research, 74(1):59–109, 2004

    work page 2004

  30. [30]

    Ghosh, S

    K. Ghosh, S. R. Nangi, Y . Kanchugantla, P. G. Rayapati, P. K. Bhowmick, and P. Goyal. Augmenting video lectures: Identifying off-topic concepts and linking to relevant video lecture segments. International Journal of Artificial Intelligence in Education, 32(2):382– 412, 2022

    work page 2022

  31. [31]

    Hellier, J

    E. Hellier, J. Edworthy, and M. S. Wogalter. Handbook of warnings, 2006

    work page 2006

  32. [32]

    C. R. Henrie, L. R. Halverson, and C. R. Graham. Measuring student engagement in technology-mediated learning: A review.Computers & Education, 90:36–53, 2015

    work page 2015

  33. [33]

    C. L. Hicks, C. L. von Baeyer, P. A. Spafford, I. van Korlaar, and B. Goodenough. The faces pain scale–revised: toward a common metric in pediatric pain measurement.Pain, 93(2):173–183, 2001

    work page 2001

  34. [34]

    Hidi and K

    S. Hidi and K. A. Renninger. The four-phase model of interest development.Educational psychologist, 41(2):111–127, 2006

    work page 2006

  35. [35]

    Hollander and S

    J. Hollander and S. Huette. Extracting blinks from continuous eye- tracking data in a mind wandering paradigm.Consciousness and Cognition, 100:103303, 2022

    work page 2022

  36. [36]

    Holmqvist, M

    K. Holmqvist, M. Nystr ¨om, R. Andersson, R. Dewhurst, H. Jarodzka, and J. Van de Weijer.Eye tracking: A comprehensive guide to methods and measures. oup Oxford, 2011

    work page 2011

  37. [37]

    Hu.A Reception Study of Machine Translated Subtitles for MOOCs

    K. Hu.A Reception Study of Machine Translated Subtitles for MOOCs. PhD thesis, Dublin City University, 2020

    work page 2020

  38. [38]

    S. Hutt, J. Hardey, R. Bixler, A. Stewart, E. Risko, and S. K. D’Mello. Gaze-based detection of mind wandering during lecture viewing.International Educational Data Mining Society, 2017

    work page 2017

  39. [39]

    Immadisetty, P

    P. Immadisetty, P. Rajesh, A. Gupta, A. M. R, S. A, and K. N. Subramanya. Multimodality in Online Education: A Comparative Study, Dec. 2023. doi: 10.48550/arXiv.2312.05797

    work page doi:10.48550/arxiv.2312.05797 2023

  40. [40]

    A. S. Imran, A. Moreno, and F. A. Cheikh. Exploiting visual cues in non-scripted lecture videos for multi-modal action recognition. In 2012 Eighth International Conference on Signal Image Technology and Internet Based Systems, pp. 8–14. IEEE, 2012

    work page 2012

  41. [41]

    Iso 3864-1:2011 graph- ical symbols — safety colours and safety signs — part 1: Design principles for safety signs and safety markings

    International Organization for Standardization. Iso 3864-1:2011 graph- ical symbols — safety colours and safety signs — part 1: Design principles for safety signs and safety markings. https://www.iso.org/ standard/51021.html, 2011

    work page 2011

  42. [42]

    S. J. Isherwood, S. J. McDougall, and M. B. Curry. Icon identifica- tion in context: The changing role of icon characteristics with user experience.Human factors, 49(3):465–476, 2007

    work page 2007

  43. [43]

    D. Jang, I. Yang, and S. Kim. Detecting mind-wandering from eye movement and oculomotor data during learning video lecture. Education Sciences, 10(3):51, 2020

    work page 2020

  44. [44]

    Jeon and N

    B. Jeon and N. Park. Dropout prediction over weeks in moocs by learning representations of clicks and videos.arXiv preprint arXiv:2002.01955, 2020

    work page arXiv 2002

  45. [45]

    M. A. Just and P. A. Carpenter. A theory of reading: from eye fixations to comprehension.Psychological Review, 87(4):329, 1980. doi: 10. 1037/0033-295X.87.4.329

    work page 1980

  46. [46]

    T. Kar, P. Kanungo, S. N. Mohanty, S. Groppe, and J. Groppe. Video shot-boundary detection: issues, challenges and solutions.Artificial Intelligence Review, 57(4):104, 2024

    work page 2024

  47. [47]

    Kattenborn, J

    T. Kattenborn, J. Leitloff, F. Schiefer, and S. Hinz. Review on convolutional neural networks (cnn) in vegetation remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 173:24–49, 2021

    work page 2021

  48. [48]

    K. R. Koedinger, J. Kim, J. Z. Jia, E. A. McLaughlin, and N. L. Bier. Learning is not a spectator sport: Doing is better than watching for learning from a mooc. InProceedings of the second (2015) ACM conference on learning@ scale, pp. 111–120, 2015

    work page 2015

  49. [49]

    Krajbich, C

    I. Krajbich, C. Armel, and A. Rangel. Visual fixations and the computation and comparison of value in simple choice.Nature neuroscience, 13(10):1292–1298, 2010

    work page 2010

  50. [50]

    Krajbich and A

    I. Krajbich and A. Rangel. Multialternative drift-diffusion model predicts the relationship between visual fixations and choice in value- based decisions.Proceedings of the National Academy of Sciences, 108(33):13852–13857, 2011

    work page 2011

  51. [51]

    Krejtz, A

    K. Krejtz, A. T. Duchowski, A. Niedzielska, C. Biele, and I. Krejtz. Eye tracking cognitive load using pupil diameter and microsaccades with fixed gaze.PloS one, 13(9):e0203629, 2018

    work page 2018

  52. [52]

    Le and T

    Q. Le and T. Mikolov. Distributed representations of sentences and documents.31st International Conference on Machine Learning, ICML 2014, 4, 05 2014

    work page 2014

  53. [53]

    Littenberg-Tobias, J

    J. Littenberg-Tobias, J. A. Ruip ´erez-Valiente, and J. Reich. Studying learner behavior in online courses with free-certificate coupons: Results from two case studies.International Review of Research in Open and Distributed Learning, 21(1):1–22, 2020

    work page 2020

  54. [54]

    C. Liu, J. Kim, and H.-C. Wang. Conceptscape: Collaborative concept mapping for video learning. InProceedings of the 2018 CHI conference on human factors in computing systems, pp. 1–12, 2018

    work page 2018

  55. [55]

    Q. Liu, X. Yang, Z. Chen, and W. Zhang. Using synchronized eye movements to assess attentional engagement.Psychological research, 87(7):2039–2047, 2023

    work page 2039

  56. [56]

    H. Luo, T. Koszalka, and M. Zuo. Investigating the effects of visual cues in multimedia instruction using eye tracking. InBlended Learning: Aligning Theory with Practices: 9th International Conference, ICBL 2016, Beijing, China, July 19-21, 2016, Proceedings 9, pp. 63–72. Springer, 2016

    work page 2016

  57. [57]

    Q. Lyu, S. Havaldar, A. Stein, L. Zhang, D. Rao, E. Wong, M. Apid- ianaki, and C. Callison-Burch. Faithful chain-of-thought reasoning. InThe 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2023), 2023

    work page 2023

  58. [58]

    Madsen, S

    J. Madsen, S. U. J ´ulio, P. J. Gucik, R. Steinberg, and L. C. Parra. Synchronized eye movements predict test scores in online video education.Proceedings of the National Academy of Sciences, 118(5):e2016980118, 2021

    work page 2021

  59. [59]

    Madsen and L

    J. Madsen and L. C. Parra. Cognitive processing of a common stimulus synchronizes brains, hearts, and eyes.PNAS nexus, 1(1):pgac020, 2022

    work page 2022

  60. [60]

    Maffei and A

    A. Maffei and A. Angrilli. Spontaneous eye blink rate: An index of dopaminergic component of sustained attention and fatigue.Interna- tional Journal of Psychophysiology, 123:58–63, 2018

    work page 2018

  61. [61]

    Malik, M

    M. Malik, M. K. Malik, K. Mehmood, and I. Makhdoom. Automatic speech recognition: a survey.Multimedia Tools and Applications, 80:9411–9457, 2021

    work page 2021

  62. [62]

    Math ˆot

    S. Math ˆot. Pupillometry: Psychology, physiology, and function.Jour- nal of cognition, 1(1):16, 2018

    work page 2018

  63. [63]

    S. J. McDougall, O. De Bruijn, and M. B. Curry. Exploring the effects of icon characteristics on user performance: The role of icon concreteness, complexity, and distinctiveness.Journal of Experimental Psychology: Applied, 6(4):291, 2000

    work page 2000

  64. [64]

    S. Mu, M. Cui, X. J. Wang, J. X. Qiao, and D. M. Tang. Learners’ attention preferences of information in online learning: An empirical study based on eye-tracking.Interactive Technology and Smart Edu- cation, 16(3):186–203, 2019

    work page 2019

  65. [65]

    Nakano, Y

    T. Nakano, Y . Yamamoto, K. Kitajo, T. Takahashi, and S. Kitazawa. Synchronization of spontaneous eyeblinks while viewing video sto- ries.Proceedings of the Royal Society B: Biological Sciences, 276(1673):3635–3644, 2009

    work page 2009

  66. [66]

    Narimani and E

    A. Narimani and E. Barber `a. Extracting course features and learner pro- filing for course recommendation systems: A comprehensive literature review.The International Review of Research in Open and Distributed Learning, 25(1):197–225, 2024

    work page 2024

  67. [67]

    Navarro, ´A

    M. Navarro, ´A. Becerra, R. Daza, R. Cobos, A. Morales, and J. Fierrez. V AAD: Visual Attention Analysis Dashboard applied to e-Learning, Sept. 2024. doi: 10.48550/arXiv.2405.20091

    work page doi:10.48550/arxiv.2405.20091 2024

  68. [68]

    J. D. Novak and A. J. Ca ˜nas. The theory underlying concept maps and how to construct and use them. 2008

    work page 2008

  69. [69]

    M. M. Nujid and D. A. Tholibon. A review of engagement strategies for massive open online courses.International Journal of Evaluation and Research in Education (IJERE), 2024. doi: 10.11591/ijere.v13i5. 29158 IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, VOL. XX, NO. X, JUNE 20XX 17

    work page doi:10.11591/ijere.v13i5 2024

  70. [70]

    A. Olsen. The tobii i-vt fixation filter.Tobii Technology, 21(4-19):5, 2012

    work page 2012

  71. [71]

    D. F. O. Onah, J. Sinclair, and R. Boyatt. Dropout rates of massive open online courses : Behavioural patterns. In L. G ´omez Chova, A. L ´opez Mart ´ınez, and I. Candel Torres, eds.,EDULEARN14 Pro- ceedings, pp. 5825–5834. IATED Academy, Barcelona, Spain, 2014

    work page 2014

  72. [72]

    Papamitsiou and A

    Z. Papamitsiou and A. A. Economides. Learning analytics and educational data mining in practice: A systematic literature review of empirical evidence.Journal of educational technology & society, 17(4):49–64, 2014

    work page 2014

  73. [73]

    P. R. Pintrich. The role of motivation in promoting and sustaining self-regulated learning.International journal of educational research, 31(6):459–470, 1999

    work page 1999

  74. [74]

    J. L. Plass, R. Moreno, and R. Br ¨unken. Cognitive load theory. 2010

    work page 2010

  75. [75]

    M. I. Posner and M. K. Rothbart. Research on attention networks as a model for the integration of psychological science.Annu. Rev. Psychol., 58(1):1–23, 2007

    work page 2007

  76. [76]

    L. Rai, Z. Yue, T. Yang, R. Shadiev, and N. Sun. General impact of MOOC assessment methods on learner engagement and performance. In2017 10th International Conference on Ubi-media Computing and Workshops (Ubi-Media), pp. 1–4, Aug. 2017. doi: 10.1109/UMEDIA. 2017.8074135

    work page doi:10.1109/umedia 2017

  77. [77]

    Ranti, W

    C. Ranti, W. Jones, A. Klin, and S. Shultz. Blink rate patterns provide a reliable measure of individual engagement with scene content. Scientific reports, 10(1):8267, 2020

    work page 2020

  78. [78]

    S. Ren, L. Yao, S. Li, X. Sun, and L. Hou. TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding. In2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14313–14323. IEEE, Seattle, W A, USA, June

    work page

  79. [79]

    doi: 10.1109/CVPR52733.2024.01357

    work page doi:10.1109/cvpr52733.2024.01357 2024

  80. [80]

    K. A. Renninger and S. Hidi.The power of interest for motivation and engagement. Routledge, 2015

    work page 2015

Showing first 80 references.