A Cognitive Load Theory (CLT) Analysis of Machine Learning Explainability, Transparency, Interpretability, and Shared Interpretability
Open accessThe DOI matches its Crossref record; 76 of the 77 references it cites were found in a registry or an index.
Abstract
Information that is complicated and ambiguous entails high cognitive load. Trying to understand such information can involve a lot of cognitive effort. An alternative to expending a lot of cognitive effort is to engage in motivated cognition, which can involve selective attention to new information that matches existing beliefs. In accordance with principles of least action related to management of cognitive effort, another alternative is to give up trying to understand new information with high cognitive load. In either case, high cognitive load can limit potential for understanding of new information and learning from new information. Cognitive Load Theory (CLT) provides a framework for relating the characteristics of information to human cognitive load. Although CLT has been developed through more than three decades of scientific research, it has not been applied comprehensively to improve the explainability, transparency, interpretability, and shared interpretability (ETISI) of machine learning models and their outputs. Here, in order to illustrate the broad relevance of CLT to ETISI, it is applied to analyze a type of hybrid machine learning called Algebraic Machine Learning (AML). This is the example because AML has characteristics that offer high potential for ETISI. However, application of CLT reveals potential for high cognitive load that can limit ETISI even when AML is used in conjunction with decision trees. Following the AML example, the general relevance of CLT…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“Accordingly, some types of AI models may only ever be “black boxes” and attempts to make them explainable may not be successful [2].”
BackgroundFrom local explanations to global understanding with explainable AI for trees
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., & Lee, S.-I. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-019-0138-9 · Cited by 10,551 · cited 2×
“Application of (SHAP) values can involve a wide variety of diagrams, including bar charts that have both positive and negative SHAP values for multiple variables represented by horizontal bars, which can be colored to indicate the extent to which each variable has a high or low feature value [74].”
BackgroundPeeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)
Adadi, A., & Berrada, M. (2018) · IEEE Access · doi:10.1109/access.2018.2870052 · Cited by 6,294 · cited 1×
“Such explainability can be summarized with the abbreviation XAI from eXplainable arti fi cial intelligence [57]. can be summarized with the abbreviation XAI from eXplainable artificial [57].”
BackgroundPolitical conservatism as motivated social cognition.
Jost, J. T., Glaser, J., Kruglanski, A. W., & Sulloway, F. J. (2003) · Psychological Bulletin · doi:10.1037/0033-2909.129.3.339 · Cited by 4,904 · cited 1×
“Accordingly, motivated social cognition [44] may lead to interpretations of machine learning models and outputs being based on what is already believed rather than on what is currently seen.”
BackgroundCognitive load theory, learning difficulty, and instructional design
Sweller, J. (1994) · Learning and Instruction · doi:10.1016/0959-4752(94)90003-5 · Cited by 3,801 · cited 2×
“Trying to understand information with high cognitive load can entail high cognitive effort that does not necessarily lead to understanding or learning [16].”
BackgroundThe economy of brain network organization
Bullmore, E., & Sporns, O. (2012) · Nature Reviews Neuroscience · doi:10.1038/nrn3214 · Cited by 3,284 · cited 2×
“Rather, research suggests that the the most economic trade-o ff between neural connectivity and wiring costs [53] mechanism for balancing bene fi ts and risks in As summarized in Figure 1, consideration of cognitive load highlights that ETISI can involve interactions between social issues and…”
BackgroundCognitive Load Theory and Instructional Design: Recent Developments
Paas, F., Renkl, A., & Sweller, J. (2003) · Educational Psychologist · doi:10.1207/s15326985ep3801_1 · Cited by 3,041 · cited 1×
“With regard to intrinsic cognitive load, within CLT it is posited that human working memory can handle only a very limited number—possibly as few as two or three—of novel interacting elements [27].”
BackgroundExplainable AI: a review of machine learning interpretability methods
Linardatos, P., Papastefanopoulos, V., & Kotsiantis, S. (2020) · Entropy · doi:10.3390/e23010018 · Cited by 2,922 · cited 2×
“More broadly, a survey of interpretability has yielded a taxonomy of interpretability methods [72].”
BackgroundPennycook, G., & Rand, D. G. (2019) · Cognition · doi:10.1016/j.cognition.2018.06.011 · Cited by 2,022 · cited 1×
“As well as motivated reasoning, the extent to which different people make different interpretations of the same information may also be influenced by lack of reasoning [49].”
BackgroundCausability and explainability of artificial intelligence in medicine
Holzinger, A., Langs, G., Denk, H., Zatloukal, K., & Müller, H. (2019) · WIREs Data Mining and Knowledge Discovery · doi:10.1002/widm.1312 · Cited by 1,885 · cited 1×
“…speci fi ed level of causal understanding with e ff ectiveness, e ffi ciency and satisfaction in a speci fi ed context of use”. has been extent to which an explanation of a statement to a human expert achieves of causal understanding with effectiveness, efficiency and satisfaction context of use” [63].”
BackgroundCan we open the black box of AI?
Castelvecchi, D. (2016) · Nature · doi:10.1038/538020a · Cited by 1,773 · cited 1×
“[69].”
Shin, D. (2021) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2020.102551 · Cited by 1,548 · cited 1×
“It has been argued that It has been argued that causability is an antecedent of explainability [62]. an antecedent of explainability [62].”
BackgroundExplainable AI: From black box to glass box
Rai, A. (2020) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-019-00710-5 · Cited by 1,317 · cited 1×
“This is summarized in well-established comparisons of metaphorical opaque “black box” computing and transparent “glass box” computing [67], which have been applied to AI [68].”
MethodPaas, F., Renkl, A., & Sweller, J. (2004) · Instructional Science · doi:10.1023/b:truc.0000021806.17516.d0 · Cited by 1,054 · cited 1×
“Cognitive load from the same information can depend upon the extent of prior knowledge, and more prior knowledge may not necessarily reduce cognitive load [28].”
BackgroundAction and behavior: a free-energy formulation
Friston, K. J., Daunizeau, J., Kilner, J., & Kiebel, S. J. (2010) · Biological Cybernetics · doi:10.1007/s00422-010-0364-z · Cited by 866
The evidence for motivated reasoning in climate change preference formation
Druckman, J. N., & McGrath, M. C. (2019) · Nature Climate Change · doi:10.1038/s41558-018-0360-1 · Cited by 733 · cited 1×
“Within motivated reasoning, different political beliefs can influence what different people consider to be credible evidence [42].”
BackgroundProduct Design for Manufacture and Assembly
Boothroyd, G., Dewhurst, P., & Knight, W. A. (2010) · CRC Press eBooks · doi:10.1201/9781420089288 · Cited by 655
Uncertainty and stress: Why it causes diseases and how it is mastered by the brain
Peters, A., McEwen, B. S., & Friston, K. (2017) · Progress in Neurobiology · doi:10.1016/j.pneurobio.2017.05.004 · Cited by 652 · cited 1×
“As energy is required to change information that is already neurologically encoded [51], less energy may be required for people to make reference to their existing internal world models than is required for reasoning about new information.”
BackgroundActive Inference: The Free Energy Principle in Mind, Brain, and Behavior
Parr, T., Pezzulo, G., & Friston, K. J. (2022) · doi:10.7551/mitpress/12441.001.0001 · Cited by 651
Hohwy, J. (2016) · Noûs · doi:10.1111/nous.12062 · Cited by 578
Recent advances in decision trees: an updated survey
Costa, V. G., & Pedreira, C. E. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-022-10275-5 · Cited by 572 · cited 1×
“However, a survey of advances in decision trees revealed that not all decision trees are equally interpretable, and some decision trees may not be interpretable [73].”
BackgroundDesign for Assembly and Disassembly
Boothroyd, G., & Alting, L. (1992) · CIRP Annals · doi:10.1016/s0007-8506(07)63249-1 · Cited by 465 · cited 1×
“The implementation of science-based design principles can bring large performance improvements in diverse sectors [79,80].”
BackgroundThe Oxford Handbook of Causation
(2009) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780199279739.001.0001 · Cited by 423
Mechanisms of motivation–cognition interaction: challenges and opportunities
Braver, T. S., Krug, M. K., Chiew, K. S., Kool, W., Westbrook, J. A., Clement, N. J., Adcock, R. A., Barch, D. M., Botvinick, M. M., Carver, C. S., et al. (2014) · Cognitive, Affective, & Behavioral Neuroscience · doi:10.3758/s13415-014-0300-0 · Cited by 391
Supporting Human-AI Teams:Transparency, explainability, and situation awareness
Endsley, M. R. (2023) · Computers in Human Behavior · doi:10.1016/j.chb.2022.107574 · Cited by 309 · cited 1×
“Accordingly, there are efforts to improve transparency [70].”
BackgroundThe black box inside the glass box: presenting computing concepts to novices
DU BOULAY, B., O'SHEA, T., & MONK, J. (1999) · International Journal of Human-Computer Studies · doi:10.1006/ijhc.1981.0309 · Cited by 274 · cited 1×
“This is summarized in well-established comparisons of metaphorical opaque “black box” computing and transparent “glass box” computing [67], which have been applied to AI [68].”
MethodOne Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques
Arya, V., Bellamy, R. K. E., Chen, P.-Y., Dhurandhar, A., Hind, M., Hoffman, S. C., Houde, S., Liao, Q. V., Luss, R., Mojsilović, A., et al. (2019) · arXiv · doi:10.48550/arxiv.1909.03012 · Cited by 268 · cited 2×
“Different people can have different Di ff erent people can have di ff erent requirements for explanations [60], and even experts may not agree about explainability [61]. for explanations [60], and even experts may not agree about explainabil-ity , to use a colloquial Hence, to use a colloquial…”
BackgroundExplainable AI for Designers: A Human-Centered Perspective on Mixed-Initiative Co-Creation
Zhu, J., Liapis, A., Risi, S., Bidarra, R., & Youngblood, G. M. (2018) · 2018 IEEE Conference on Computational Intelligence and Games (CIG) · doi:10.1109/cig.2018.8490433 · Cited by 255 · cited 2×
“This is because within tools that are used by people [59].”
MethodActive inference on discrete state-spaces: A synthesis
Da Costa, L., Parr, T., Sajid, N., Veselic, S., Neacsu, V., & Friston, K. (2020) · Journal of Mathematical Psychology · doi:10.1016/j.jmp.2020.102447 · Cited by 226 · cited 1×
“Such reluctance to believe a diagnosis can be framed within the general tendency for people to want to continue to survive in preferred states [47].”
BackgroundIs there a better term than “medically unexplained symptoms”?
Creed, F., Guthrie, E., Fink, P., Henningsen, P., Rief, W., Sharpe, M., & White, P. (2010) · Journal of Psychosomatic Research · doi:10.1016/j.jpsychores.2009.09.004 · Cited by 207 · cited 1×
“For example, it has been argued that the term “medically unexplained symptoms” is a barrier to improved care because it is conceptually ambiguous [35].”
BackgroundActive inference on discrete state-spaces: A synthesis
Costa, L. D., Parr, T., Sajid, N., Veselic, S., Neacsu, V., & Friston, K. J. (2020) · UCL Discovery (University College London) · Cited by 204
Gerjets, P., Scheiter, K., & Catrambone, R. (2006) · Learning and Instruction · doi:10.1016/j.learninstruc.2006.02.007 · Cited by 178 · cited 1×
“For example, CLT research findings indicate that modular structuring can entail lower intrinsic cognitive load [75].”
BackgroundBalmaña, J., Digiovanni, L., Gaddam, P., Walsh, M. F., Joseph, V., Stadler, Z. K., Nathanson, K. L., Garber, J. E., Couch, F. J., Offit, K., et al. (2016) · Journal of Clinical Oncology · doi:10.1200/jco.2016.68.4316 · Cited by 174 · cited 1×
“There can be different interpretations of large amounts of information [9] and of diagrams, such as tree diagrams, that are intended to simplify the presentation of information [10].”
BackgroundExplainable Artificial Intelligence for Human Decision Support System in the Medical Domain
Knapič, S., Malhi, A., Saluja, R., & Främling, K. (2021) · Machine Learning and Knowledge Extraction · doi:10.3390/make3030037 · Cited by 171
The semantic distance task: Quantifying semantic distance with semantic network path length.
Kenett, Y. N., Levi, E., Anaki, D., & Faust, M. (2017) · Journal of Experimental Psychology: Learning, Memory, and Cognition · doi:10.1037/xlm0000391 · Cited by 165 · cited 1×
“Semantic distance can be considered in terms of path length comprising the number of steps needed to traverse from one word to another word in the same path [32].”
BackgroundLane Change Decision-making through Deep Reinforcement Learning with Rule-based Constraints
Wang, J., Zhang, Q., Zhao, D., & Chen, Y. (2019) · 2019 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852110 · Cited by 163 · cited 1×
“That is, ML that encompasses predefinition of rules and ongoing learning from data [21,22].”
BackgroundPolitical conservatism as motivated social cognition
Jost, J. T., Glaser, J., Sulloway, F. J., & Kruglanski, A. W. (2018) · Routledge eBooks · doi:10.4324/9781315175867-5 · Cited by 155
Decade of progress in motor functional neurological disorder: Continuing the momentum
Perez, D. L., Edwards, M. J., Nielsen, G., Kozlowska, K., Hallett, M., & LaFrance, Jr. (2021) · Journal of Neurology, Neurosurgery & Psychiatry · doi:10.1136/jnnp-2020-323953 · Cited by 149 · cited 1×
“For example, the term “patient label avoidance” refers to patients’ efforts to distance themselves from a label, i.e., a diagnosis, because it can be perceived as being socially unacceptable [45].”
BackgroundKliegr, T., Bahník, Š., & Fürnkranz, J. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103458 · Cited by 139 · cited 1×
“However, interpretability will not necessarily lead to different people agreeing a shared interpretation of the same information [4].”
BackgroundThe Cognitive Load of Geographic Information
Bunch, R. L., & Lloyd, R. E. (2006) · The Professional Geographer · doi:10.1111/j.1467-9272.2006.00527.x · Cited by 131 · cited 2×
“Insights from CLT are already applied in a variety of fields in order to try to reduce the cognitive load of information [13–15].”
BackgroundAutomated de novo molecular design by hybrid machine intelligence and rule-driven chemical synthesis
Button, A. L., Merk, D., Hiss, J. A., & Schneider, G. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0067-7 · Cited by 121 · cited 1×
“That is, ML that encompasses predefinition of rules and ongoing learning from data [21,22].”
BackgroundRewiring the connectome: Evidence and effects
Bennett, S. H., Kirby, A. J., & Finnerty, G. T. (2018) · Neuroscience & Biobehavioral Reviews · doi:10.1016/j.neubiorev.2018.03.001 · Cited by 116 · cited 1×
“…a new configuration is inversely proportional to the energy associated with moving to that new configuration [48], and acceptance of some new information could have to involve extensive neural reconfiguration in what can be described as rewiring the connectome of many neural connections [52].”
BackgroundPaying the brain's energy bill
Padamsey, Z., & Rochefort, N. L. (2023) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2022.102668 · Cited by 114 · cited 1×
“However, human beings have evolved to be economical in the expenditure of brain energy [50].”
BackgroundIntrinsic and Extraneous Cognitive Load
Sweller, J., Ayres, P., & Kalyuga, S. (2011) · Cognitive Load Theory · doi:10.1007/978-1-4419-8126-4_5 · Cited by 107 · cited 1×
“High cognitive load can come from the addition of intrinsic load and extraneous load [26].”
BackgroundSystem Transparency in Shared Autonomy: A Mini Review
Alonso, V., & de la Puente, P. (2018) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2018.00083 · Cited by 107 · cited 1×
“The term transparency is associated with the observability of system behavior [66].”
BackgroundCOGAM: Measuring and Moderating Cognitive Load in Machine Learning Model Explanations
Abdul, A., von der Weth, C., Kankanhalli, M., & Lim, B. Y. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376615 · Cited by 96 · cited 1×
“Recently, there has been some limited recognition that consideration of CLT could improve explainability and interpretability [17–20].”
BackgroundWorld model learning and inference
Friston, K., Moran, R. J., Nagai, Y., Taniguchi, T., Gomi, H., & Tenenbaum, J. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.09.011 · Cited by 90 · cited 1×
“Different interpretations of the same information can arise because different people have different internal models of self in the world, which, for brevity, can be referred to as world models [11].”
BackgroundOn the Conceptual Ambiguity Surrounding Perceived Message Effectiveness
Yzer, M. C., LoRusso, S. M., & Nagler, R. H. (2014) · Health Communication · doi:10.1080/10410236.2014.974131 · Cited by 83 · cited 1×
“Terms that are widely used can be conceptually ambiguous [34].”
BackgroundI’ll see it when i believe it: motivated numeracy in perceptions of climate change risk
Nurse, M. S., & Grant, W. J. (2020) · Environmental Communication · doi:10.1080/17524032.2019.1618364 · Cited by 83 · cited 1×
“Within motivated numeracy, people may align interpretations of data with their existing political attitudes even if they are highly numerate people [43].”
BackgroundScalability of Network Visualisation from a Cognitive Load Perspective
Yoghourdjian, V., Yang, Y., Dwyer, T., Lawrence, L. M., Wybrow, M., & Marriott, K. (2020) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2020.3030459 · Cited by 81 · cited 1×
“Some people may give up trying to understand information if it comprises too many elements [29].”
BackgroundHuman-centered explainability for life sciences, healthcare, and medical informatics
Dey, S., Chakraborty, P., Kwon, B. C., Dhurandhar, A., Ghalwash, M. F., Suárez, F., Ng, K., Sow, D., Varshney, K. R., & Meyer, P. (2022) · Patterns · doi:10.1016/j.patter.2022.100493 · Cited by 72 · cited 4×
“…can have different Di ff erent people can have di ff erent requirements for explanations [60], and even experts may not agree about explainability [61]. for explanations [60], and even experts may not agree about explainabil-ity , to use a colloquial Hence, to use a colloquial automotive analogy,…”
BackgroundInfluentialHooshyar, D., Azevedo, R., & Yang, Y. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6010028 · Cited by 72 · cited 1×
“Improving the explainability , transparency , and interpretability of machine learning are recognized as important goals [1–3].”
BackgroundWang, Y., Wang, J., Liu, X., & Zhu, T. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.661213 · Cited by 70 · cited 2×
“The data set is from a previous study conducted by [71].”
MethodBorder Bias: The Belief That State Borders Can Protect Against Disasters
Mishra, A., & Mishra, H. (2010) · Psychological Science · doi:10.1177/0956797610385950 · Cited by 61
Integrating cognitive load theory with other theories, within and beyond educational psychology
Hanham, J., Castro‐Alonso, J. C., & Chen, O. (2023) · British Journal of Educational Psychology · doi:10.1111/bjep.12612 · Cited by 50 · cited 2×
“Insights from CLT are already applied in a variety of fields in order to try to reduce the cognitive load of information [13–15].”
BackgroundSweller, J., Ayres, P., & Kalyuga, S. (2011) · Springer eBooks · doi:10.1007/978-1-4419-8126-4_11 · Cited by 45 · cited 2×
“Unlike the split-a tt ention e ff ect, the information in each format is intelligible on its own [76]. that is redundant because it does not facilitate understanding or example, the same information content can be presented in more than one the Nonetheless, cognitive e ff ort is involved in…”
BackgroundThe good, the bad, and the red: implicit color-valence associations across cultures
Kawai, C., Zhang, Y., Lukács, G., Chu, W., Zheng, C., Gao, C., Gozli, D. G., Wang, Y., & Ulrich Ansorge, A. (2022) · Psychological Research · doi:10.1007/s00426-022-01697-5 · Cited by 45 · cited 1×
“Presentational ambiguities include color and layout [36,37].”
Evaluating the Interpretability of Generative Models by Interactive Reconstruction
Ross, A., Chen, N., Hang, E. Z., Glassman, E. L., & Doshi-Velez, F. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445296 · Cited by 40 · cited 1×
“These have focused on consideration of intrinsic cognitive load in interpretation of algorithms [18], element interactivity in evaluating the interpretability of generative models [19], and cognitive load of contextual information for human–AI collaboration [20].”
BackgroundNovick, L. R., & Catley, K. M. (2014) · Science Education · doi:10.1002/sce.21097 · Cited by 32 · cited 1×
“There can be different interpretations of large amounts of information [9] and of diagrams, such as tree diagrams, that are intended to simplify the presentation of information [10].”
BackgroundRamarapu, N. K., Frolick, M. N., Wilkes, R. B., & Wetherbe, J. C. (1997) · Decision Sciences · doi:10.1111/j.1540-5915.1997.tb01333.x · Cited by 32 · cited 1×
“Presentational ambiguities include color and layout [36,37].”
Causation and Explanation in Aristotle
Stein, N. (2011) · Philosophy Compass · doi:10.1111/j.1747-9991.2011.00436.x · Cited by 27
Chen, Y., Lin, Q., Liao, X., Zhou, C., & He, Y. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2013232118 · Cited by 25 · cited 2×
“…ff between neural connectivity and wiring costs [53] mechanism for balancing bene fi ts and risks in As summarized in Figure 1, consideration of cognitive load highlights that ETISI can involve interactions between social issues and biological issues as well as technical issues. the connectome [54].”
BackgroundPhonological ambiguity and lexical ambiguity: Effects on visual and auditory word recognition.
Frost, R., Feldman, L. B., & Katz, L. (1990) · Journal of Experimental Psychology Learning Memory and Cognition · doi:10.1037//0278-7393.16.4.569 · Cited by 24
Lombardi, O., Fortín, S., Holik, F., et al. (2017) · Cambridge University Press eBooks · doi:10.1017/9781316494233 · Cited by 19
Human Delegation Behavior in Human-AI Collaboration: The Effect of Contextual Information
Spitzer, P., Holstein, J., Hemmer, P., Vössing, M., Kühl, N., Martin, D., & Satzger, G. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3710999 · Cited by 18 · cited 3×
“Nonetheless, recently, there has been some studies that relate cognitive load to interpretability [18–20].”
BackgroundThe segmented presentation of visually structured texts: Effects on text comprehension
Lemarié, J., Eyrolle, H., & Cellier, J. (2007) · Computers in Human Behavior · doi:10.1016/j.chb.2007.02.016 · Cited by 16 · cited 1×
“Presentational ambiguities can also arise from the formats in which written text is presented [38].”
BackgroundWriting Accessible Theory in Ecology and Evolution: Insights from Cognitive Load Theory
Ou, W. J.-A., Henriques, G. J. B., Senthilnathan, A., Ke, P., Grainger, T. N., & Germain, R. M. (2021) · BioScience · doi:10.1093/biosci/biab133 · Cited by 16
Fox, S. (2013) · Management Research Review · doi:10.1108/01409171311306427 · Cited by 15 · cited 1×
“Ambiguities can be conceptual, presentational, and/or linguistic [33].”
BackgroundSelf-citationAlgebraic Machine LearningPreprint
Martín-Maroto, F., & de Polavieja, G. G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.05252 · Cited by 15
Functional Gait Disorders: Clinical presentations, Phenotypes and Implications for treatment
Issak, S., Kanaan, R., Nielsen, G., Fini, N. A., & Williams, G. P. (2023) · Brain Injury · doi:10.1080/02699052.2023.2165158 · Cited by 12 · cited 1×
“Apropos, some people who have functional gait disorders may not believe a diagnosis due to concerns about stigma [46].”
BackgroundSheehan, B., Kaufman, D. R., Stetson, P. D., & Currie, L. M. (2009) · Europe PMC (PubMed Central) · Cited by 11
Garcke, J., & Roscher, R. (2023) · Machine Learning and Knowledge Extraction · doi:10.3390/make5010010 · Cited by 10 · cited 1×
“Improving the explainability , transparency , and interpretability of machine learning are recognized as important goals [1–3].”
BackgroundA note on pragmatic principles of least effort
Carston, R. (2005) · Cited by 7
Semantic Embeddings in Semilattices
Martín-Maroto, F., & de Polavieja, G. G. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.12618 · Cited by 7
Cognitive Task Analysis as a Basis for Instructional Design
Means, B. (2020) · Routledge eBooks · doi:10.4324/9781315044712-4 · Cited by 5 · cited 1×
“As cognitive overload is detrimental, cognitive task analysis techniques have been developed in order to assess cognitive loads and how they can be reduced [30].”
BackgroundLalor, J. P., & Guo, H. M. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.10207 · Cited by 5
Fox, S., & Rey, V. F. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6010027 · Cited by 2 · cited 1×
“For example, in healthcare, conflicting interpretations need to be avoided because they may lead to poor treatment outcomes [12].”
BackgroundSelf-citation
Research works printed but not linked: 1
- Pound, R. (2013). Interpretations of Legal History, Harvard University Press.
Cited by
Hamida, S. U., Chowdhury, M. J. M., Chakraborty, N. R., Biswas, K., & Sami, S. K. (2024) · Big Data and Cognitive Computing · doi:10.3390/bdcc8110149 · Cited by 95
Mapping theoretical approaches: a scoping review of data analytics in higher education
Ncube, M. M., & Ngulube, P. (2025) · Discover Education · doi:10.1007/s44217-025-00647-8 · Cited by 13
“Fox and Rey [101] applied CLT principles to design clear and transparent machine learning explanations, reducing cognitive load and demonstrating CLT’s value in designing effective data-driven systems.”
A unified approach to extract interpretable rules from tree ensembles via Integer Programming
Bonasera, L., & Carrizosa, E. (2025) · Computers & Operations Research · doi:10.1016/j.cor.2025.107283 · Cited by 9
Thi Thuy An, N. G. O., Chau, H. K. L., Tran, N. P. N., & Bui, C. T. (2025) · Acta Psychologica · doi:10.1016/j.actpsy.2025.106095 · Cited by 13
Chen, B., & Ahmed, S. (2026) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2026.2623213 · Cited by 3
“These findings align with CLT, which posits that reducing users’ extraneous processing demands enhances their ability to engage with complex systems and sustain positive behavioral intentions (Fox & Rey, 2024).”
Influential
Metadata
- Authors
- Fox, S., & Rey, V. F.
- Affiliations
- VTT Technical Research Centre of Finland (FI)
- DFKI German Research Center for Artificial Intelligence, 67663 Kaiserslautern, Germany
- Corresponding author
- Fox, Stephen
- ORCID
- Fox, Stephen
- Venue
- Machine Learning and Knowledge Extraction
- Publisher
- MDPI AG
- Published
- 2024-07-02
- Volume
- 6
- Issue
- 3
- Pages
- 1494-1509
- ISSN
- 2504-4990 (ISSN-L)
- OpenAlex
- W4400284842
- Cited by
- 22
- References
- 75
- Citations by year
- 2026: 10 · 2025: 9 · 2024: 3
- FWCI
- 3.26
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Machine Learning and Knowledge Extraction (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- European Union (EU) (952091)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Visual and Cognitive Learning Processes
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Keywords
- cognitive load theory, machine learning explainability, transparency, interpretability, decision tree, motivated cognition, least action principle, SHAP, lime
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.