CoChat
Sign Up
Cited by 39Occupational Health and BurnoutStress and Burnout ResearchCOVID-19 and Mental Health

Burnout, Resilience, and COVID-19 among Teachers: Predictive Capacity of an Artificial Neural Network

Open access
Martínez-Ramón, Juan Pedro, Morales-Rodríguez, Francisco Manuel, Pérez-López, Sergio·2021·Applied Sciences
DOI 10.3390/app11178206
Open this paper in CoChat — free accountOpen PDF

Abstract

Emotional exhaustion, cynicism, and work inefficiency are three dimensions that define burnout syndrome among teachers. On another note, resilience can be understood as the ability to adapt to the environment and overcome adverse situations. In addition, COVID-19 has provided a threatening environment that has led to the implementation of resilience strategies to struggle with burnout and cope with the virus. The aim of this study was to analyze the relationship between resilience, burnout dimensions, and variables associated with COVID-19 through the design of an artificial neural network architecture. For this purpose, the Maslach Burnout Inventory-General Survey (MBI-GS), the Brief Resilience Coping Scale (BRCS), and a questionnaire on stress towards COVID-19 were administered to 419 teachers from secondary schools in southeastern Spain (292 females; 69.7%). The results showed that 30.8% suffered from burnout (high emotional exhaustion, high cynicism, and low professional efficacy) and that 38.7% had a high level of resilience, with an inverse relationship between both constructs. Likewise, we modelled an ANN able to predict burnout syndrome among 97.4% of teachers based on its dimensions, resilience, sociodemographic variables, and the stress generated by COVID-19. Our conclusions shed some light on the efficacy of relying on artificial intelligence in the educational field to predict the psychological situation of teachers and take early action.

AI snapshot

Written from the paper’s full text.

TL;DR

This cross-sectional study examined burnout, resilience, and COVID-19-related stress among 419 secondary school teachers in southeastern Spain and designed an artificial neural network to predict burnout presence versus absence. The ANN correctly classified 97.4% of holdout cases, with professional efficacy, cynicism, marital status, and age contributing most to prediction.

Key findings

  • 30.8% of teachers met criteria for burnout (high emotional exhaustion, high cynicism, low professional efficacy); resilience levels were high for 38.7% (162), medium for 41.1% (172), and low for 20.3% (85).
  • Burnout and resilience were inversely related: emotional exhaustion correlated with cynicism (r = 0.521, p < 0.001) and negatively with resilience (r = -0.228, p < 0.01); cynicism correlated negatively with resilience (r = -0.357, p < 0.001); professional efficacy correlated positively with resilience (r = 0.489, p < 0.001).
  • The ANN predicted burnout presence/absence with 93% correct in training, 93.2% in testing, and 97.4% in holdout; AUC was 0.983 for both presence and absence of burnout.
  • Normalized importance for predictors was highest for professional efficacy (100%), followed by cynicism (15.9%), marital status (15.5%), age (14.6%), resilience (10.2%), COVID-19 stress (6.1%), and gender (4.6%).

Methods

  • Quantitative, cross-sectional, ex post facto design; online questionnaires administered in January–February 2021 to 419 Compulsory Secondary Education public school teachers in the Region of Murcia, Spain (292 female, 69.7%; mean age 44.37, SD = 9.385; mean teaching experience 15.33, SD = 10.059).
  • Instruments: Maslach Burnout Inventory-General Survey (MBI-GS; 15 items; Cronbach’s alpha 0.8 in this study), Brief Resilience Coping Scale (BRCS; 4 items; alpha 0.73), and an ad hoc Stress Evaluation Questionnaire for COVID-19 (SEQ-COVID-19; six Likert-type stress items plus sociodemographic variables).
  • Analysis used SPSS v24 for descriptive/inferential statistics, Pearson correlations, Student’s t-tests, and a multilayer perceptron ANN with backpropagation; dependent variable was burnout presence versus absence, with cases split into 64.4% training, 17.4% testing, and 18.1% holdout.

Limitations

  • The authors state that focusing on secondary schools limits generalization to other educational stages, and that collecting data at one specific pandemic time prevents observing changes as situations normalize.
  • The authors also state that the analysis omitted important aspects such as the influence of age, teaching experience, and the correlation between resilience and burnout, and that contrasting COVID-19 variables with burnout and resilience was difficult due to scarce prior research.
  • Evident from the text: the study relies on self-report and an ad hoc COVID-19 stress measure, and participation was 5.06% of the target population, which may limit representativeness despite meeting the calculated minimum sample size.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/app11178206

Cites

61 of 61 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 8 cited sources checked · 0 supported · 0 flagged

  • Findingown data

    38.7% of the participating teachers had high resilience.

    “38.7% had a high level of resilience”
    • Also stated in: § 3.1. Analysis of the Presence of Burnout Syndrome and Resilience Level · plain
      “38.7% (162) of the faculty had high resilience”
    Quote in the paperNot a substantial claim
  • Findingown data

    The artificial neural network had a correct prediction percentage of 93.2% in the testing sample.

    “93.2% in the testing sample”
    Quote in the paperSubstantial claim
  • Findingown data

    The burnout dimension had a direct and significant correlation with cynicism (r = 0.521, p < 0.001).

    “the burnout dimension had a direct and significant correlation with cynicism (r = 0.521, p < 0.001)”
    Quote in the paperNot a substantial claim
  • Findingown data

    41.1% of the participating teachers had medium resilience.

    “41.1% (172) had medium resilience”
    Quote in the paperNot a substantial claim
  • Findingown data

    The cynicism dimension had a statistically significant inverse correlation with resilience (r = -0.357, p < 001).

    “with resilience (r = -0.357,p < 001)”
    Quote in the paperNot a substantial claim
  • The quote only partly states this claim. 2
  • Classified as probably not a substantial claim. 10
  • May combine two claims. 14

  • The quote only partly states this claim.

    Findingown data

    30.8% of the participating Compulsory Secondary Education teachers in the Region of Murcia suffered from burnout syndrome, defined as high emotional exhaustion, high cynicism, and low professional efficacy.

    “The results showed that 30.8% suffered from burnout (high emotional exhaustion, high cynicism, and low professional efficacy)”
    • Also stated in: § 3.1. Analysis of the Presence of Burnout Syndrome and Resilience Level · plain
      “Regarding burnout syndrome, 30.8% (120) of the participants were found to suffer from burnout syndrome (high burnout, high cynicism, and low efficacy).”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Findingnone given

    Teachers in the study show worrying levels of emotional exhaustion, cynicism, and low job satisfaction.

    “It is necessary to pay more attention to the psychological well-being of teachers because it is a group with worrying levels of emotional exhaustion, cynicism, and low job satisfaction.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    129 teachers (30.8%) presented burnout syndrome, characterized by a high rate of exhaustion and cynicism as well as low efficacy.

    “It was found that 129 teachers (30.8%) presented burnout syndrome, that is, a high rate of exhaustion and cynicism as well as low efficacy.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: The sample of secondary school teachers in the Region of Murcia is representative of the population of secondary school teachers in that region.

  • May combine two claims.

    Findingown data

    As burnout increases, resilience decreases, and vice versa.

    “When establishing possible correlations between the constructs of burnout and resilience, it was concluded that as one increases, the other decreases, i.e., the greater the burnout syndrome, the less resilience and vice versa.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    The artificial neural network predicted and classified 97.4% of cases, including cases it had not previously analyzed.

    “In fact, our ANN was able to predict and classify 97.4% of the experimental cases.”
    • Also stated in: § 5. Conclusions · plain
      “The ANN achieved a high predictive capacity, reaching a probability of 97.4% when classifying cases that the network had not previously analyzed.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    The emotional exhaustion dimension was affected in all COVID-19 cases, with significant differences in each of these variables.

    “In this case, the emotional exhaustion dimension was affected in all COVID-19 cases, obtaining significant differences in each of these variables.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Education is one of the professional sectors most affected by the burnout phenomenon.

    “one of the sectors most affected by the burnout phenomenon is education [20]”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [20] Méndez, I., Martínez-Ramón, J.P., Ruiz-Esteban, C., and García-Fernández, J.M. (2020). Latent profiles of burnout, self-esteem and depressive symptomatology among teachers. Int. J. Environ. Res. Public Health, 17. source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Premisecitation

    Artificial intelligence is proving to be an effective tool for predicting with great precision the possibility of an event occurring.

    “artificial intelligence is proving to be an effective tool for predicting with great precision the possibility of an event occurring [60]”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [60] Qin, 2019, Advances and opportunities in machine learning for process data analytics, Comput. Chem. Eng. source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Compulsory Secondary Education is the educational stage in which burnout symptoms are most evident.

    “Of all the educational stages where the syndrome can emerge, it seems that Compulsory Secondary Education is the one in which burnout symptoms are most evident [4].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [4] Pinel, 2019, Investigación sobre el burnout en docentes españoles: Una revisión sobre factores asociados e instrumentos de evaluación, Bordón. Rev. Pedag. source

      Not checked in the free run.

  • May combine two claims.

    Interpretationown data

    The artificial neural network was able to self-learn and self-improve.

    “Our data confirm that our neural network was able to self-learn and self-improve.”
    Quote in the paperNot a substantial claim

  • Classified as probably not a substantial claim.

    Premisecitation

    People with high resilience are less likely to suffer burnout syndrome.

    “In general terms, it seems that people with high resilience are less likely to suffer burnout syndrome [52]”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [52] Rico, A., Ferrer, M.C., and Sánchez, S. (2016). Resiliencia versus síndrome del burnout en cuidadores de pacientes geriátricos. Perspectivas y Análisis de la Salud, ASUNIVEP.

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Teachers who have few resilient strategies are more vulnerable to stress and burnout, while those with high resilient capacities can cushion the impacts of their work environment.

    “Those teachers who have few resilient strategies are more vulnerable to the effects that stress can produce and to the extent of burnout syndrome, while those who have high resilient capacities are able to develop personal resources that allow them to cushion the impacts produced by their work environment [50]”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [50] Ferradás, M.D.M., Freire, C., García-Bertoa, A., Núñez, J.C., and Rodríguez, S. (2019). Teacher profiles of psychological capital and their relationship with burnout. Sustainability, 11. source

      Not checked in the free run.

  • May combine two claims.

    Interpretationown data

    H4 was only partially confirmed: depending on the burnout dimension, there may or may not be significant differences with variables associated with COVID-19.

    “Therefore, h4 is only partially confirmed.”
    • Also stated in: § 4. Discussion · hedged
      “depending on the dimension of burnout, there may or may not be significant differences.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: The ad hoc SEQ-COVID-19 questionnaire validly measures teachers' stress towards COVID-19.

  • May combine two claims.

    Premisecitation

    The BRCS is a reliable and valid instrument.

    “It is a reliable and valid instrument.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [65] Sinclair, 2004, The development and psychometric evaluation of the Brief Resilient Coping Scale, Assessment source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    Informed consent was obtained from all subjects involved in the study.

    “Informed Consent Statement: Informed consent was obtained from all subjects involved in the study.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    The MBI-GS is a reliable and valid instrument.

    “This questionnaire is reliable and valid.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [9] Maslach, C., and Jackson, S.E. (1986). Maslach Burnout Inventory, Consulting Psychologists Press. [2nd ed.].

      Not checked in the free run.

  • The quote only partly states this claim.

    Study design and conductown data

    The MBI-GS showed a Cronbach's alpha of 0.8 in this research.

    “In global terms, the Cronbach's alpha obtained in this research was 0.8.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductown data

    The BRCS showed a Cronbach's alpha of 0.73 in this research.

    “In the present investigation a Cronbach's alpha of 0.73 was obtained.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationown data

    Relying on artificial intelligence in the educational field is efficacious for predicting the psychological situation of teachers and taking early action.

    “Our conclusions shed some light on the efficacy of relying on artificial intelligence in the educational field to predict the psychological situation of teachers and take early action.”
    Quote in the paperSubstantial claim
    • Rests on an assumption: The artificial neural network's predictive performance generalizes to teachers beyond the holdout sample.

  • May combine two claims.

    Premisecitation

    Artificial neural networks allow the development of models with a high predictive capacity and autonomous learning capacity.

    “artificial neural networks allow the development of models with a high predictive capacity and autonomous learning capacity [61]”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [61] Hahn, 2019, Portraits of communication in neuronal networks, Nat. Rev. Neurosci. source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    The research had a high percentage of participation.

    “In spite of these limitations, this research has been carried out successfully and has had a high percentage of participation.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationreasoning

    Subjects with medium-low resilience are more likely to suffer from burnout syndrome because they do not possess sufficient resilient skills.

    “Thus, subjects with medium-low resilience are more likely to suffer from this syndrome as they do not possess sufficient resilient skills.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Study design and conductnone given

    In the data analysis, certain important aspects were left out, such as the influence of age on burnout syndrome, teaching experience, and the correlation between resilience and the appearance of the syndrome.

    “On the other hand, in the data analysis, it should be noted that certain aspects of importance are left out, such as, for example, the influence of age on burnout syndrome, teaching experience, and the correlation between resilience and the appearance of the syndrome, among others.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationnone given

    Focusing the research on secondary schools makes it difficult to generalize the results to other educational stages.

    “Regarding the limitations of this study, on the one hand, focusing the research on secondary schools makes it difficult to generalize the results to other educational stages.”
    Quote in the paperNot a substantial claim
24 of 24

  • The paper relies on this without support.

    The ad hoc SEQ-COVID-19 questionnaire validly measures teachers' stress towards COVID-19.

    “An ad hoc instrument designed by the authors of the present study that included items on the stress situation in the face of COVID-19 as well as various sociodemographic variables aimed at the participating teachers (gender, age, years of experience, marital status, and whether they had offspring) (Appendix A).”

  • The paper relies on this without support.

    The sample of 419 teachers is representative of the population of 8278 Compulsory Secondary Education teachers in the Region of Murcia.

    “The general population selected for the present study consisted of 8278 teachers of Compulsory Secondary Education in the public sector in the Region of Murcia, Spain.Once the sample was selected, the participation of a group of 419 subjects was achieved, which meant a participation of 5.06% of the teaching staff.”
    “Our sample data allow us to establish a very varied group by forming an analysis of the constructs that encompass the entire teaching population.”

  • The paper relies on this without support.

    The artificial neural network's predictive performance generalizes to teachers beyond the holdout sample.

    “Our conclusions shed some light on the efficacy of relying on artificial intelligence in the educational field to predict the psychological situation of teachers and take early action.”
    “the neural network used a previously unused sample to test the predictive efficiency, obtaining even higher results.”

  • The paper relies on this without support.

    The sample of secondary school teachers in the Region of Murcia is representative of the population of secondary school teachers in that region.

    “the analysis carried out throughout this research has made it possible to determine the levels of burnout among secondary school teachers in the Region of Murcia.”
4 of 4

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

  • Burnout count does not match the reported percentage

    Major

    The results report 120 teachers with burnout as 30.8% of the 419 participants, but 120/419 is 28.6%. The conclusion instead reports 129 teachers, which does correspond to 30.8%.

    Reported 30.8 · recomputed 28.639618

  • Conclusion calls a nonsignificant efficacy result significant

    Major

    The conclusion identifies stress about students' families becoming infected as significantly associated with professional efficacy, whereas Table 1 gives that comparison p = 0.362.

  • Burnout-cynicism correlation changes sign

    Major

    The same pair of dimensions is reported as positively correlated in one sentence and inversely correlated in the next, with different correlation coefficients.

  • Conclusion overlooks significant cynicism result for family contagion

    Minor

    The conclusion says only stress about one's own infection showed a significant difference in cynicism, but Table 1 reports p = 0.005 for family contagion.

  • Burnout outcome codes are reversed in the figure note

    Minor

    The methods assign 0 to presence and 1 to absence of burnout; the Figure 1 note assigns those codes the opposite meanings.

5 of 5

Cites

Flagged first, then by citations

2 of the 63 references couldn’t be matched to a known paper.

Research works printed but not linked: 10

  1. 2019, Analysis of burnout syndrome in teachers of preschool, middle school and high school for prevention and treatment, Rev. Electr. Educare, 23, 1
  2. Maslach, C., and Jackson, S.E. (1986). Maslach Burnout Inventory, Consulting Psychologists Press. [2nd ed.].
  3. World Health Organization (2018). Proceedings of the International Statistical Classification of Diseases and Related Health Problems, WHO. [11th ed.]. Available online: https://icd.who.int/browse11/l-m/en.
  4. 2016, La investigación sobre el síndrome de burnout en Latinoamérica entre 2000 y el 2010, Psicol. Caribe, 33, 113
  5. Extremera, 2017, Estado de la Cuestión Sobre Inteligencia Emocional y Burnout en el Profesorado por Países, Año de Publicación, Ciclos Educativos e Instrumentos de Evaluación, Profr. Rev. Currículum Form. Profr., 21, 371
  6. Noreña, H. (2017). Estrés Académico y Estrategias de Afrontamiento en Estudiantes de Primer, Segundo y Tercer Semestre de la Facultad de Ingeniería de la Universidad de Antioquia. [Master’s Thesis, University of Antioquia]. Available online: https://bit.ly/375gY9i.
  7. 2015, Propiedades psicométricas y estructura factorial del BRCS en una muestra de personas mayores españolas, An. Psicol., 31, 1030
  8. Pando, 2006, Factores psicosociales y síndrome de burnout en docentes de la Universidad del Valle de Atemejac, Guadalaraja, México, Salud Tabasco, 12, 523
  9. Guerrero, 2008, Fuentes de estrés y síndrome de burnout en orientadores de institutos de Enseñanza Secundaria, Rev. Educ., 347, 229
  10. Hidalgo, 2019, Burnout, resiliencia y compromiso laboral en maestros de educación especial, Educ. Cienc., 8, 48

Cited by

Sorted by citations

Related

Authors
Martínez-Ramón, J. P., Morales-Rodríguez, F. M., & Pérez-López, S.
Affiliations
  • Universidad de Murcia (ES)
  • Departament of Educational and Developmental Psychology, Faculty of Psychology, Campus de la Cartuja, University of Granada, 18071 Granada, Spain
Corresponding author
Martínez-Ramón, Juan Pedro
ORCID
Venue
Applied Sciences
Publisher
MDPI AG
Published
2021-09-03
Volume
11
Issue
17
Pages
8206
ISSN
2076-3417 (ISSN-L)
DOI
10.3390/app11178206
OpenAlex
W3197225064
Semantic Scholar
7346e7cdba4ddec814f51799eca27cd06fe52d6a
Cited by
32
References
63
Citations by year
2026: 3 · 2025: 5 · 2024: 6 · 2023: 10 · 2022: 8
FWCI
9.88
Type
journal article
Language
en
Open access
Licence
Locations
  • Applied Sciences (publishedVersion, cc-by)
  • Institutional Repository of the University of Granada (University of Granada) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Health Sciences › Health Professions › Occupational Therapy › Occupational Health and Burnout
  • Social Sciences › Psychology › Social Psychology › Stress and Burnout Research
  • Social Sciences › Psychology › Clinical Psychology › COVID-19 and Mental Health
Keywords
teacher burnout, resilience, COVID-19 stress, emotional exhaustion, cynicism, professional efficacy, burnout prediction, artificial neural networks, secondary school teachers

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review