pith. sign in

arxiv: 2606.04254 · v1 · pith:3EWIQMDGnew · submitted 2026-06-02 · 💻 cs.HC · cs.CY

Behavioral and Performance Indicators of Depression and Anxiety in Electronic Learning Systems

Arya VarastehNezhad , Fattaneh Taghiyareh This is my paper

Pith reviewed 2026-06-28 08:00 UTC · model grok-4.3

classification 💻 cs.HC cs.CY
keywords depressionanxietylearning management systembehavioral indicatorse-learningMoodlestudent well-beingmental health
0
0 comments X

The pith

LMS log patterns link to higher depression and anxiety scores among university students.

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

The paper tests whether routine data from a Moodle learning management system can be mined for behavioral signals of depression and anxiety. It combines event logs, grades, and Beck inventory scores from 97 computer engineering students and applies statistical tests to a wide range of extracted indicators. Significant associations appear: higher depression tracks with shifted activity timing, longer sessions, and late homework submissions, while higher anxiety tracks with more concentrated engagement and different session structures. The work argues that these patterns could supply non-clinical early signals of student strain inside existing course platforms.

Core claim

Several indicators extracted from LMS event logs were significantly associated with depression and anxiety. Higher depression scores correlated with shifted temporal activity patterns, longer session durations, and shorter homework submission lead times. Higher anxiety scores correlated with concentrated temporal engagement and session-based differences. These links were obtained after descriptive statistics, t-tests with FDR correction, effect sizes, and Spearman correlations on data from 97 students whose inventory scores showed no sex or year differences.

What carries the argument

A broad set of behavioral and performance indicators spanning temporal engagement, session structure, deadline-related behavior, page-refresh patterns, and LMS navigation, extracted from raw Moodle event logs and tested for association with BDI-II and BAI scores.

Load-bearing premise

The assumption that behavioral indicators taken from LMS logs accurately capture mental-health-related strain without large confounding by course design, academic performance, or other unmeasured variables, and that the self-reported inventory scores reliably measure depression and anxiety.

What would settle it

A replication study on a new cohort that finds no significant associations between the reported temporal, session, and submission indicators and the inventory scores after controlling for course and performance variables would falsify the central associations.

read the original abstract

This study investigates whether behavioral and performance indicators derived from a Moodle-based learning management system are associated with university students' depression and anxiety in two undergraduate Computer Engineering courses. Using a quantitative observational design, LMS event logs, academic records, and self-reported Beck Depression Inventory-II and Beck Anxiety Inventory scores from 97 students were integrated. A broad set of behavioral and performance indicators spanning temporal engagement, session structure, deadline-related behavior, page-refresh patterns, and LMS navigation was extracted from raw event logs and analyzed using descriptive statistics, independent-samples t-tests with Benjamini-Hochberg FDR correction, effect sizes, and Spearman correlations; inventory scores were confirmed invariant by sex and academic year. Several indicators were significantly associated with depression and anxiety. Higher depression was associated with shifted temporal activity patterns, longer session durations, and shorter homework submission lead times, while higher anxiety was associated with concentrated temporal engagement and session-based differences. These findings suggest that routine LMS data can provide meaningful behavioral signals related to student well-being and may support earlier educational awareness of students who experience mental-health-related strain. At the same time, such indicators should be interpreted as contextual and non-diagnostic markers rather than as substitutes for clinical assessment.

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 reports an observational study integrating Moodle LMS event logs, academic records, and self-reported BDI-II/BAI scores from 97 students in two undergraduate Computer Engineering courses. It extracts behavioral indicators (temporal engagement, session structure, deadline behavior, navigation patterns) and finds several significant associations via independent-samples t-tests (Benjamini-Hochberg FDR correction), effect sizes, and Spearman correlations: higher depression linked to shifted activity timing, longer sessions, and shorter homework lead times; higher anxiety linked to concentrated temporal patterns and session differences. The abstract concludes that routine LMS data can yield contextual, non-diagnostic signals of mental-health-related strain.

Significance. If the reported associations prove robust after appropriate confounder control, the work could support development of non-invasive, scalable indicators for student well-being monitoring in e-learning platforms, complementing existing self-report methods. The inclusion of FDR correction, effect sizes, and invariance checks by sex/academic year is methodologically sound and strengthens the statistical reporting.

major comments (1)
  1. [Abstract/Results] Abstract and Results: Although academic records were collected and integrated, the described analyses rely exclusively on unadjusted independent-samples t-tests (with FDR) and Spearman correlations between LMS indicators and inventory scores. No covariate adjustment, partial correlations, or stratification using performance metrics (grades, GPA) is reported. This is load-bearing for the central claim that the indicators reflect depression/anxiety-related strain rather than academic performance confounds, as poorer performance could jointly elevate inventory scores and alter behaviors such as session length or submission timing.
minor comments (1)
  1. [Abstract] The abstract would benefit from explicitly naming the sample size (97) and course context in the opening sentence for immediate clarity.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback on our observational study. The concern regarding potential confounding by academic performance is well-taken, and we address it directly below. We have prepared a revised manuscript that incorporates the suggested adjustments.

read point-by-point responses

  1. Referee: [Abstract/Results] Abstract and Results: Although academic records were collected and integrated, the described analyses rely exclusively on unadjusted independent-samples t-tests (with FDR) and Spearman correlations between LMS indicators and inventory scores. No covariate adjustment, partial correlations, or stratification using performance metrics (grades, GPA) is reported. This is load-bearing for the central claim that the indicators reflect depression/anxiety-related strain rather than academic performance confounds, as poorer performance could jointly elevate inventory scores and alter behaviors such as session length or submission timing.

    Authors: We agree that academic performance is a plausible confound and that the absence of adjustment limits causal interpretation of the associations. Academic records were collected primarily to derive the performance indicators mentioned in the methods (e.g., grades and submission outcomes), but were not used for covariate control in the reported t-tests and correlations. In the revised manuscript we will add (1) partial Spearman correlations between each LMS indicator and BDI-II/BAI scores controlling for course GPA and final grade, and (2) a supplementary table showing the change in effect sizes after adjustment. We will also note in the discussion that residual associations after GPA control strengthen the case for LMS-specific behavioral signals. These additions directly address the load-bearing concern while preserving the exploratory nature of the original analyses. revision: yes

Circularity Check

0 steps flagged

No significant circularity; direct empirical associations only

full rationale

The paper contains no mathematical derivations, equations, fitted parameters, or predictions that could reduce to inputs by construction. All reported results are straightforward statistical associations (independent-samples t-tests with FDR, Spearman correlations, effect sizes) computed directly from LMS event logs, academic records, and self-reported BDI-II/BAI scores collected from 97 students. No self-citations are invoked as load-bearing premises for any uniqueness theorem or ansatz, and the analysis does not rename known results or smuggle assumptions via prior work. The derivation chain is therefore self-contained as standard observational data processing.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The paper uses established psychological assessment tools and standard statistical practices without introducing new free parameters or invented entities.

axioms (2)
  • domain assumption Beck Depression Inventory-II and Beck Anxiety Inventory scores validly measure depression and anxiety levels
    Relies on these standard self-report tools being accurate proxies.
  • domain assumption The extracted behavioral indicators from event logs are meaningful and not artifacts of the system or course structure
    Assumes the indicators like session duration and temporal patterns capture relevant behavior.

pith-pipeline@v0.9.1-grok · 5745 in / 1378 out tokens · 31563 ms · 2026-06-28T08:00:47.281547+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

45 extracted references · 41 canonical work pages

  1. [1]

    Learning Management System (LMS) Research During 1991 -2021: How Technology Affects Education,

    B. Prahani, J. Alfin, A. Fuad, H. Saphira, E. Hariyono, and N. Suprapto, “Learning Management System (LMS) Research During 1991 -2021: How Technology Affects Education,” International Journal of Emerging Technologies in Learning (iJET), vol. 17, no. 17, pp. 28–49, Sep. 2022

    1991

  2. [2]

    Mental disorders among college students in the World Health Organization World Mental Health Surveys,

    R. P. Auerbach et al., “Mental disorders among college students in the World Health Organization World Mental Health Surveys,” Psychological Medicine, vol. 46, no. 14, pp. 2955–2970, Oct. 2016, doi: 10.1017/S0033291716001665

    work page doi:10.1017/s0033291716001665 2016

  3. [3]

    A systematic review of studies of depression prevalence in university students,

    A. K. Ibrahim, S. J. Kelly, C. E. Adams, and C. Glazebrook, “A systematic review of studies of depression prevalence in university students,” Journal of Psychiatric Research, vol. 47, no. 3, pp. 391 –400, Mar. 2013, doi: 10.1016/j.jpsychires.2012.11.015

    work page doi:10.1016/j.jpsychires.2012.11.015 2013

  4. [4]

    Systematic Review of Depression, Anxiety, and Other Indicators of Psychological Distress Among U.S. and Canadian Medical Students,

    L. N. Dyrbye, M. R. Thomas, and T. D. Shanafelt, “Systematic Review of Depression, Anxiety, and Other Indicators of Psychological Distress Among U.S. and Canadian Medical Students,” Acad Med, vol. 81, no. 4, pp. 354–373, Apr. 2006, doi: 10.1097/00001888-200604000-00009

    work page doi:10.1097/00001888-200604000-00009 2006

  5. [5]

    The Impact of Depressive and Anxiety Symptoms on Academic Achievement among Undergraduate University Students: A Systematic Review,

    S. Awadalla, E. B. Davies, and C. Glazebrook, “The Impact of Depressive and Anxiety Symptoms on Academic Achievement among Undergraduate University Students: A Systematic Review,” OBM Neurobiology, vol. 8, no. 4, pp. 1 –36, Dec. 2024, doi: 10.21926/obm.neurobiol.2404261

    work page doi:10.21926/obm.neurobiol.2404261 2024

  6. [6]

    The Effects of Stress and Anxiety in Technology -Based Learning Environments,

    M. N. Mian, G. Mohammadi, and N. Marcus, “The Effects of Stress and Anxiety in Technology -Based Learning Environments,” Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 46, no. 0, 2024, Accessed: May 26, 2026. [Online]. Available: https://escholarship.org/uc/item/6b84b33b

    2024

  7. [7]

    Pekrun and L

    R. Pekrun and L. Linnenbrink -Garcia, Eds., International Handbook of Emotions in Education, 0 ed. Routledge, 2014. doi: 10.4324/9780203148211

    work page doi:10.4324/9780203148211 2014

  8. [8]

    Mining LMS data to develop an ‘early warning system’ for educators: A proof of concept,

    L. P. Macfadyen and S. Dawson, “Mining LMS data to develop an ‘early warning system’ for educators: A proof of concept,” Computers & Education, vol. 54, no. 2, pp. 588 –599, Feb. 2010, doi: 10.1016/j.compedu.2009.09.008

    work page doi:10.1016/j.compedu.2009.09.008 2010

  9. [9]

    Course signals at Purdue: Using learning analytics to increase student success,

    K. Arnold and M. Pistilli, “Course signals at Purdue: Using learning analytics to increase student success,” ACM International Conference Proceeding Series, Apr. 2012, doi: 10.1145/2330601.2330666

    work page doi:10.1145/2330601.2330666 2012

  10. [10]

    Prediction of At -Risk Students Using Learning Analytics: A Literature Review,

    K. C. Li, B. T. M. Wong, and H. T. Chan, “Prediction of At -Risk Students Using Learning Analytics: A Literature Review,” in Technology in Education. Innovative Practices for the New Normal, S. K. S. Cheung, F. L. Wang, N. Paoprasert, P. Charnsethikul, K. C. Li, and K. Phusavat, Eds., Sin gapore: Springer Nature, 2024, pp. 119 –128. doi: 10.1007/978-981-9...

    work page doi:10.1007/978-981-99-8255-4_11 2024

  11. [11]

    R. Dai, T. Kannampallil, S. Kim, V. Thornton, L. Bierut, and C. Lu, Detecting Mental Disorders with Wearables: A Large Cohort Study. 2023, p. 51. doi: 10.1145/3576842.3582389

    work page doi:10.1145/3576842.3582389 2023

  12. [12]

    Exploring the Relationship Between Gameplay Log Data and Depression & Anxiety,

    S. Elyasi, A. V. Nezhad, and F. Taghiyareh, “Exploring the Relationship Between Gameplay Log Data and Depression & Anxiety,” in 2023 14th International Conference on Information and Knowledge Technology (IKT), Dec. 2023, pp. 50–56. doi: 10.1109/IKT62039.2023.10433060

    work page doi:10.1109/ikt62039.2023.10433060 2023

  13. [13]

    Detection and Analysis of Mental Health Illness using Social Media,

    R. Qayyum, H. Afzal, K. Mahmood, and N. Iltaf, “Detection and Analysis of Mental Health Illness using Social Media,” in 2023 International Conference on Communication Technologies (ComTech), Mar. 2023, pp. 34–41. doi: 10.1109/ComTech57708.2023.10165143

    work page doi:10.1109/comtech57708.2023.10165143 2023

  14. [14]

    From Play to Prediction: Assessing Depression and Anxiety in Players Behavior with Machine Learning Models,

    S. Elyasi, A. VarastehNezhad, and F. Taghiyareh, “From Play to Prediction: Assessing Depression and Anxiety in Players Behavior with Machine Learning Models,” IJSG, vol. 12, no. 1, pp. 83–102, Feb. 2025, doi: 10.17083/ijsg.v12i1.897

    work page doi:10.17083/ijsg.v12i1.897 2025

  15. [15]

    Internet -based Questionnaire Assessment: Appropriate Use in Clinical Contexts,

    T. Buchanan, “Internet -based Questionnaire Assessment: Appropriate Use in Clinical Contexts,” Cognitive Behaviour Therapy, vol. 32, no. 3, pp. 100–109, Jan. 2003, doi: 10.1080/16506070310000957

    work page doi:10.1080/16506070310000957 2003

  16. [16]

    Students’ Perceptions of Learning Analytics for Mental Health Support: Qualitative Study,

    A. Freccero, M. Onwunle, J. Elliott, N. Pod der, J. P. D. Oliveira, and L. H. Dewa, “Students’ Perceptions of Learning Analytics for Mental Health Support: Qualitative Study,” JMIR Formative Research, vol. 9, no. 1, p. e70327, Aug. 2025, doi: 10.2196/70327

    work page doi:10.2196/70327 2025

  17. [17]

    Prevalence of depression and anxiety among undergraduate university students in low - and middle -income countries: a systematic review protocol,

    J. January, M. Madhombiro, S. Chipamaunga, S. Ray, A. Chingono, and M. Abas, “Prevalence of depression and anxiety among undergraduate university students in low - and middle -income countries: a systematic review protocol,” Syst Rev, vol. 7, no. 1, p. 57, Apr. 2018, doi: 10.1186/s13643-018-0723-8

    work page doi:10.1186/s13643-018-0723-8 2018

  18. [18]

    Engineering graduate students’ mental health: A scoping literature review,

    S. Bork and J. L. Mondisa, “Engineering graduate students’ mental health: A scoping literature review,” Journal of Engineering Education, vol. 111, pp. 665–702, May 2022, doi: 10.1002/jee.20465

    work page doi:10.1002/jee.20465 2022

  19. [19]

    Socioeconomic inequalities and ment al health problems in children and adolescents: A systematic review,

    F. Reiss, “Socioeconomic inequalities and ment al health problems in children and adolescents: A systematic review,” Social Science & Medicine, vol. 90, pp. 24 –31, Aug. 2013, doi: 10.1016/j.socscimed.2013.04.026

    work page doi:10.1016/j.socscimed.2013.04.026 2013

  20. [20]

    What is the impact of mental health-related stigma on help-seeking? A systematic review of quantitative and qualitative studies,

    S. Clement et al., “What is the impact of mental health-related stigma on help-seeking? A systematic review of quantitative and qualitative studies,” Psychological Medicine, vol. 45, no. 1, pp. 11 –27, Jan. 2015, doi: 10.1017/S0033291714000129

    work page doi:10.1017/s0033291714000129 2015

  21. [21]

    AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models’ Responses to Depression, Anxiety, and Stress Queries,

    A. VarastehNezhad, R. Tavasoli, S. Elyasi, M. LotfiNia, and H. Farbeh, “AI in Mental Health: Emotional and Sentiment Analysis of Large Language Models’ Responses to Depression, Anxiety, and Stress Queries,” Aug. 15, 2025, arXiv: arXiv:2508.11285. doi: 10.48550/arXiv.2508.11285

    work page doi:10.48550/arxiv.2508.11285 2025

  22. [22]

    Outcomes of work–life balance on job satisfaction, life satisfaction and mental health: A study across seven cultures,

    J. M. Haar, M. Russo, A. Suñe, and A. Ollier -Malaterre, “Outcomes of work–life balance on job satisfaction, life satisfaction and mental health: A study across seven cultures,” Journal of Vocational Behavior, vol. 85, no. 3, pp. 361–373, Dec. 2014, doi: 10.1016/j.jvb.2014.08.010

    work page doi:10.1016/j.jvb.2014.08.010 2014

  23. [23]

    An in formation processing model of anxiety: Automatic and strategic processes,

    A. T. Beck and D. A. Clark, “An in formation processing model of anxiety: Automatic and strategic processes,” Behaviour Research and Therapy, vol. 35, no. 1, pp. 49 –58, Jan. 1997, doi: 10.1016/S0005 - 7967(96)00069-1

    work page doi:10.1016/s0005 1997

  24. [24]

    College Students with Depressive Symptoms with and without Fatigue: Differences in Functioning, Suicidality, Anxiety, and Depressive Severity,

    M. Nyer et al., “College Students with Depressive Symptoms with and without Fatigue: Differences in Functioning, Suicidality, Anxiety, and Depressive Severity,” Annals of Clinical Psychiatry, vol. 27, no. 2, pp. 100–108, May 2015, doi: 10.1177/104012371502700204

    work page doi:10.1177/104012371502700204 2015

  25. [25]

    Longitudinal effects of stress in an academic context on psychological well -being, physiological markers, health behaviors, and academic performance in university students,

    J. C. Benítez -Agudelo, D. Restrepo, E. Navarro -Jimenez, a nd V. J. Clemente-Suárez, “Longitudinal effects of stress in an academic context on psychological well -being, physiological markers, health behaviors, and academic performance in university students,” BMC Psychol, vol. 13, no. 1, p. 753, Jul. 2025, doi: 10.1186/s40359-025-03041-z

    work page doi:10.1186/s40359-025-03041-z 2025

  26. [26]

    A Systematic Literature Review on Anxiety Among Undergraduate Students: Causes and Coping Strategies,

    S. Rastogi, S. Gupta, D. Deepak, B. N. Mishra, R. Gore, and V. Singh, “A Systematic Literature Review on Anxiety Among Undergraduate Students: Causes and Coping Strategies,” Annals of Neurosciences, p. 09727531251366078, Sep. 2025, doi: 10.1177/09727531251366078

    work page doi:10.1177/09727531251366078 2025

  27. [27]

    An Assessment of Learning Management System Use in Higher Education: Perspectives from a Comprehensive Sample of Teachers and Students,

    P. D. Simon, J. Jiang, L. K. Fryer, R. B. King, and C. E. Frondozo, “An Assessment of Learning Management System Use in Higher Education: Perspectives from a Comprehensive Sample of Teachers and Students,” Tech K now Learn, vol. 30, no. 2, pp. 741 –767, Jun. 2025, doi: 10.1007/s10758-024-09734-5

    work page doi:10.1007/s10758-024-09734-5 2025

  28. [28]

    Transition to online learning during the COVID -19 pandemic,

    D. J. Lemay, P. Bazelais, and T. Doleck, “Transition to online learning during the COVID -19 pandemic,” Computers in Human Behavior Reports, vol. 4, p. 100130, Aug. 2021, doi: 10.1016/j.chbr.2021.100130. 13

    work page doi:10.1016/j.chbr.2021.100130 2021

  29. [29]

    E -learning enhancement through educational data mining with Covid -19 outbreak period in backdrop: A review,

    K. Aulakh, R. K. Roul, and M. Kaushal, “E -learning enhancement through educational data mining with Covid -19 outbreak period in backdrop: A review,” International Journal of Educational Development, vol. 101, p. 102814, Sep. 2023, doi: 10.1016/j.ijedudev.2023.102814

    work page doi:10.1016/j.ijedudev.2023.102814 2023

  30. [30]

    Enhancing Learners’ Experience Through Extending Learning Systems,

    T. P. Tran and D. Meacheam, “Enhancing Learners’ Experience Through Extending Learning Systems,” IEEE Trans. Learning Technol., vol. 13, no. 3, pp. 540–551, Jul. 2020, doi: 10.1109/TLT.2020.2989333

    work page doi:10.1109/tlt.2020.2989333 2020

  31. [31]

    Models for early prediction of at-risk students in a course using standards-based grading,

    F. Marbouti, H. A. Diefes -Dux, and K. Madhavan, “Models for early prediction of at-risk students in a course using standards-based grading,” Computers & Education, vol. 103, pp. 1 –15, Dec. 2016, doi: 10.1016/j.compedu.2016.09.005

    work page doi:10.1016/j.compedu.2016.09.005 2016

  32. [32]

    Using learning analytics to develop early-warning system for at -risk students,

    G. Akçapına r, A. Altun, and P. Aşkar, “Using learning analytics to develop early-warning system for at -risk students,” Int J Educ Technol High Educ, vol. 16, no. 1, p. 40, Oct. 2019, doi: 10.1186/s41239 -019- 0172-z

    work page doi:10.1186/s41239 2019

  33. [33]

    Students’ sense -making of pe rsonalised feedback based on learning analytics,

    L.-A. Lim et al., “Students’ sense -making of pe rsonalised feedback based on learning analytics,” AJET, vol. 36, no. 6, pp. 15 –33, Dec. 2020, doi: 10.14742/ajet.6370

    work page doi:10.14742/ajet.6370 2020

  34. [34]

    Open Social Student Modeling for Personalize d Learning,

    P. Brusilovsky, S. Somyurek, J. Guerra, R. Hosseini, V. Zadorozhny, and P. J. Durlach, “Open Social Student Modeling for Personalize d Learning,” IEEE Trans. Emerg. Topics Comput., vol. 4, no. 3, pp. 450 – 461, Jul. 2016, doi: 10.1109/TETC.2015.2501243

    work page doi:10.1109/tetc.2015.2501243 2016

  35. [35]

    PALS2: Pedagogically Adaptive Learning System based on Learning Styles,

    M. Siadaty and F. Taghiyareh, “PALS2: Pedagogically Adaptive Learning System based on Learning Styles,” in Seventh IEEE International Conference on Advanced Learning Technologies (ICALT 2007), Nigata, Japan: IEEE, Jul. 2007, pp. 616 –618. doi: 10.1109/ICALT.2007.198

    work page doi:10.1109/icalt.2007.198 2007

  36. [36]

    The potential and pitfalls of learning analytics as a tool for supporting student wellbeing,

    S. J. Ahern, “The potential and pitfalls of learning analytics as a tool for supporting student wellbeing,” Journal of Learning and Teaching in Higher Education, vol. 1, no. 2, pp. 165–172, 2018

    2018

  37. [37]

    Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study,

    R. E. Diaz -Ramos, I. Noriega, L. A. Trejo, E. Stroulia, and B. Cao, “Using Wearable Devices and Speech Data for Personalized Machine Learning in Early Detection of Mental Disorders: Protocol for a Participatory Research Study,” JMIR Research Protocols, vol. 12, no. 1, p. e48210, Nov. 2023, doi: 10.2196/48210

    work page doi:10.2196/48210 2023

  38. [38]

    An in -depth exploration of machine learning methods for mental health state detection: a s ystematic review and analysis,

    M. J. Hasan et al., “An in -depth exploration of machine learning methods for mental health state detection: a s ystematic review and analysis,” Front. Digit. Health, vol. 7, Jan. 2026, doi: 10.3389/fdgth.2025.1724348

    work page doi:10.3389/fdgth.2025.1724348 2026

  39. [39]

    Student wellbeing and mental health: the opportunities in learning analytics

    M. Hall, “Student wellbeing and mental health: the opportunities in learning analytics”

  40. [40]

    Beck Depression Inventory–II

    A. T. Beck, R. A. Steer, and G. Brown, “Beck Depression Inventory–II.” Sep. 12, 2011. doi: 10.1037/t00742-000

    work page doi:10.1037/t00742-000 2011

  41. [41]

    Beck Anxiety Inventory

    A. T. Beck, N. Epstein, G. Brown, and R. Steer, “Beck Anxiety Inventory.” Jan. 09, 2012. doi: 10.1037/t02025-000

    work page doi:10.1037/t02025-000 2012

  42. [42]

    Manual for the Beck Depression Inventory-II

    B. AT, “Manual for the Beck Depression Inventory-II.” 1996. Accessed: May 28, 2026. [Online]. Available: https://cir.nii.ac.jp/crid/1370564063990947215

    work page arXiv 1996

  43. [43]

    Effect size estimates: Current use, calculations, and interpretation,

    C. O. Fritz, P. E. Morris, and J. J. Richler, “Effect size estimates: Current use, calculations, and interpretation,” Journal of Experimental Psychology: General, vol. 141 , no. 1, pp. 2 –18, 2012, doi: 10.1037/a0024338

    work page doi:10.1037/a0024338 2012

  44. [44]

    Correlation Coefficients: Appropriate Use and Interpretation,

    P. Schober, C. Boer, and L. A. Schwarte, “Correlation Coefficients: Appropriate Use and Interpretation,” Anesthesia & Analgesia, vol. 126, no. 5, pp. 1763 –1768, May 2018, doi: 10.1213/ANE.0000000000002864

    work page doi:10.1213/ane.0000000000002864 2018

  45. [45]

    Prediction: Yes

    Y. Benjamini and Y. Hochberg, “Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing,” Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 57, no. 1, pp. 289–300, Jan. 1995, doi: 10.1111/j.2517-6161.1995.tb02031.x. APPENDIX A: Summary of Statistically Supported Behavioral and Performance I...

    work page doi:10.1111/j.2517-6161.1995.tb02031.x 1995