{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:41:07Z","timestamp":1775504467654,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2024,2,27]],"date-time":"2024-02-27T00:00:00Z","timestamp":1708992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency-Mirai Program","doi-asserted-by":"publisher","award":["JPMJMI20D7"],"award-info":[{"award-number":["JPMJMI20D7"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Understanding the association between subjective emotional experiences and physiological signals is of practical and theoretical significance. Previous psychophysiological studies have shown a linear relationship between dynamic emotional valence experiences and facial electromyography (EMG) activities. However, whether and how subjective emotional valence dynamics relate to facial EMG changes nonlinearly remains unknown. To investigate this issue, we re-analyzed the data of two previous studies that measured dynamic valence ratings and facial EMG of the corrugator supercilii and zygomatic major muscles from 50 participants who viewed emotional film clips. We employed multilinear regression analyses and two nonlinear machine learning (ML) models: random forest and long short-term memory. In cross-validation, these ML models outperformed linear regression in terms of the mean squared error and correlation coefficient. Interpretation of the random forest model using the SHapley Additive exPlanation tool revealed nonlinear and interactive associations between several EMG features and subjective valence dynamics. These findings suggest that nonlinear ML models can better fit the relationship between subjective emotional valence dynamics and facial EMG than conventional linear models and highlight a nonlinear and complex relationship. The findings encourage emotion sensing using facial EMG and offer insight into the subjective\u2013physiological association.<\/jats:p>","DOI":"10.3390\/s24051536","type":"journal-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T03:37:57Z","timestamp":1709091477000},"page":"1536","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Machine Learning-Based Interpretable Modeling for Subjective Emotional Dynamics Sensing Using Facial EMG"],"prefix":"10.3390","volume":"24","author":[{"given":"Naoya","family":"Kawamura","sequence":"first","affiliation":[{"name":"Computational Cognitive Neuroscience Laboratory, Graduate School of Informatics, Kyoto University, Yoshida-Honmachi, Sakyo, Kyoto 606-8501, Japan"},{"name":"Psychological Process Team, Guardian Robot Project, RIKEN, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5335-1272","authenticated-orcid":false,"given":"Wataru","family":"Sato","sequence":"additional","affiliation":[{"name":"Computational Cognitive Neuroscience Laboratory, Graduate School of Informatics, Kyoto University, Yoshida-Honmachi, Sakyo, Kyoto 606-8501, Japan"},{"name":"Psychological Process Team, Guardian Robot Project, RIKEN, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koh","family":"Shimokawa","sequence":"additional","affiliation":[{"name":"Psychological Process Team, Guardian Robot Project, RIKEN, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3352-4225","authenticated-orcid":false,"given":"Tomohiro","family":"Fujita","sequence":"additional","affiliation":[{"name":"Multimodal Data Recognition Research Team, Guardian Robot Project, RIKEN, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3799-4550","authenticated-orcid":false,"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[{"name":"Multimodal Data Recognition Research Team, Guardian Robot Project, RIKEN, 2-2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2024,2,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1080\/13683500.2014.975679","article-title":"Current and potential methods for measuring emotion in tourism experiences: A review","volume":"18","author":"Li","year":"2015","journal-title":"Curr. Issues Tour."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1093\/mind\/os-IX.34.188","article-title":"What is an emotion?","volume":"9","author":"James","year":"1884","journal-title":"Mind"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1037\/0033-295X.101.2.211","article-title":"The varieties of emotional experience: A meditation on James-Lange theory","volume":"101","author":"Lang","year":"1994","journal-title":"Psychol. Rev."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.biopsycho.2009.10.006","article-title":"Feelings and the body: The Jamesian perspective on autonomic specificity of emotion","volume":"84","author":"Friedman","year":"2010","journal-title":"Biol. Psychol."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Sato, W., Kochiyama, T., and Yoshikawa, S. (2020). Physiological correlates of subjective emotional valence and arousal dynamics while viewing films. Biol. Psychol., 157.","DOI":"10.1016\/j.biopsycho.2020.107974"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5757","DOI":"10.1038\/s41598-021-85163-z","article-title":"Emotional valence sensing using a wearable facial EMG device","volume":"11","author":"Sato","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sato, W., and Kochiyama, T. (2022). Exploration of emotion dynamics sensing using trapezius EMG and fingertip temperature. Sensors, 22.","DOI":"10.3390\/s22176553"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"525","DOI":"10.1037\/0022-3514.67.3.525","article-title":"Pleasure-arousal theory and the intensity of emotions","volume":"67","author":"Reisenzein","year":"1994","journal-title":"J. Pers. Soc. Psychol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1248","DOI":"10.1016\/S0006-3223(98)00275-3","article-title":"Emotion, motivation, and anxiety: Brain mechanisms and psychophysiology","volume":"44","author":"Lang","year":"1998","journal-title":"Biol. Psychiatry"},{"key":"ref_10","unstructured":"Elder, J., Nisbet, R., and Miner, G. (2009). Handbook of Statistical Analysis and Data Mining Applications, Academic Press."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e000396","DOI":"10.1136\/bmjmed-2022-000396","article-title":"Non-linear predictor outcome associations","volume":"2","author":"Ho","year":"2023","journal-title":"BMJ Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1109\/T-AFFC.2011.9","article-title":"Continuous prediction of spontaneous affect from multiple cues and modalities in valence-arousal space","volume":"2","author":"Nicolaou","year":"2011","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/TAFFC.2015.2436926","article-title":"Analysis of EEG signals and facial expressions for continuous emotion detection","volume":"7","author":"Soleymani","year":"2016","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"19061","DOI":"10.1073\/pnas.1917036117","article-title":"Machine learning uncovers the most robust self-report predictors of relationship quality across 43 longitudinal couples studies","volume":"117","author":"Joel","year":"2020","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1191","DOI":"10.1177\/02654075211047004","article-title":"Identifying the strongest self-report predictors of sexual satisfaction using machine learning","volume":"39","author":"Vowels","year":"2022","journal-title":"J. Soc. Pers. Relat."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1080\/00224499.2021.1967846","article-title":"Is infidelity predictable? Using explainable machine learning to identify the most important predictors of infidelity","volume":"59","author":"Vowels","year":"2022","journal-title":"J. Sex Res."},{"key":"ref_18","unstructured":"Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., and Garnett, R. (2017). Advances in Neural Information Processing Systems 30, Curran Associates, Inc."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Xie, H., Liu, L., and Yue, H. (2022). Modeling the effect of streetscape environment on crime using street view images and interpretable machine-learning technique. Int. J. Environ. Res. Public Health, 19.","DOI":"10.3390\/ijerph192113833"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhu, T., Liu, X., Wang, J., Kou, R., Hu, Y., Yuan, M., Yuan, C., Luo, L., and Zhang, W. (2023). Explainable machine-learning algorithms to differentiate bipolar disorder from major depressive disorder using self-reported symptoms, vital signs, and blood-based markers. Comput. Methods Programs Biomed., 240.","DOI":"10.1016\/j.cmpb.2023.107723"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Dickinson, Q., and Meyer, J.G. (2022). Positional SHAP (PoSHAP) for interpretation of machine learning models trained from biological sequences. PLoS Comput. Biol., 18.","DOI":"10.1371\/journal.pcbi.1009736"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1080\/02699939508408966","article-title":"Emotion elicitation using films","volume":"9","author":"Gross","year":"1995","journal-title":"Cogn. Emot."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"863","DOI":"10.2224\/sbp.2007.35.7.863","article-title":"Emotion elicitation effect of films in a Japanese sample","volume":"35","author":"Sato","year":"2007","journal-title":"Soc. Behav. Pers."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1037\/0022-3514.57.3.493","article-title":"Affect grid: A single-item scale of pleasure and arousal","volume":"57","author":"Russell","year":"1989","journal-title":"J. Pers. Soc. Psychol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1037\/1528-3542.5.2.175","article-title":"The tie that binds? Coherence among emotion experience, behavior, and physiology","volume":"5","author":"Mauss","year":"2005","journal-title":"Emotion"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Tyralis, H., and Papacharalampous, G. (2017). Variable selection in time series forecasting using random forests. Algorithms, 10.","DOI":"10.3390\/a10040114"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1002\/widm.1114","article-title":"Mining data with random forests: Current options for real-world applications","volume":"4","author":"Ziegler","year":"2014","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_28","first-page":"307","article-title":"17. A value for n-person games","volume":"Volume II","author":"Shapley","year":"1953","journal-title":"Contributions to the Theory of Games (AM-28)"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","article-title":"Explaining prediction models and individual predictions with feature contributions","volume":"41","author":"Kononenko","year":"2014","journal-title":"Knowl. Inf. Syst."},{"key":"ref_30","unstructured":"JASP Team (JASP, 2020). JASP, Version 0.14.1; Computer Software."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Siirtola, P., Tamminen, S., Chandra, G., Ihalapathirana, A., and R\u00f6ning, J. (2023). Predicting emotion with biosignals: A comparison of classification and regression models for estimating valence and arousal level using wearable sensors. Sensors, 23.","DOI":"10.3390\/s23031598"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"6831167","DOI":"10.1155\/2022\/6831167","article-title":"Bus single-trip time prediction based on ensemble learning","volume":"2022","author":"Huang","year":"2022","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Oyeleye, M., Chen, T., Titarenko, S., and Antoniou, G. (2022). A predictive analysis of heart rates using machine learning techniques. Int. J. Environ. Res. Public Health, 19.","DOI":"10.3390\/ijerph19042417"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1002\/mar.20621","article-title":"Purchase behavior and psychophysiological responses to different price levels","volume":"30","author":"Somervuori","year":"2013","journal-title":"Psychol. Mark."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.physbeh.2017.08.006","article-title":"Playing a rigged game: Inequality\u2019s effect on physiological stress responses","volume":"180","author":"Shapiro","year":"2017","journal-title":"Physiol. Behav."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"106","DOI":"10.2307\/1415404","article-title":"The James-Lange theory of emotions: A critical examination and an alternative theory","volume":"39","author":"Cannon","year":"1927","journal-title":"Am. J. Psychol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.biopsycho.2013.12.013","article-title":"Is there consistency and specificity of autonomic changes during emotional episodes? Guidance from the Conceptual Act Theory and psychophysiology","volume":"98","author":"Quigley","year":"2014","journal-title":"Biol. Psychol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1177\/1754073913501395","article-title":"More on James and the physical basis of emotion","volume":"6","author":"Reisenzein","year":"2014","journal-title":"Emot. Rev."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3333","DOI":"10.1038\/s41598-023-29280-x","article-title":"Modulation of amygdala activity for emotional faces due to botulinum toxin type A injections that prevent frowning","volume":"13","author":"Stark","year":"2023","journal-title":"Sci. Rep."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/5\/1536\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T14:05:59Z","timestamp":1760105159000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/24\/5\/1536"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,27]]},"references-count":39,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["s24051536"],"URL":"https:\/\/doi.org\/10.3390\/s24051536","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,27]]}}}