Modeling Social Anxiety, Attentional Bias, and Metacognitive Beliefs with Supervised Learning Algorithms

Authors

    Josep Bosch Borras * Department of Educational Psychology, School of Information Sciences, University of Illinois at Urbana-Champaign, Champaign, IL, USA boschborras-josep@gmail.com
    Zarley Mett Department of Psychology, Clark University, Worcester, Massachusetts, USA
    Marlenne Reynoso-Calderon Department of Psychology, University of Toronto, Canada

Keywords:

Social Anxiety, Metacognitive Beliefs, Attentional Bias, Supervised Machine Learning

Abstract

Objective: The objective of this study was to utilize supervised machine learning algorithms to model and predict the severity of social anxiety based on the complex, non-linear interplay between multidimensional metacognitive beliefs and objective chronometric measures of attentional bias. Methods and Materials: A cross-sectional, predictive study design was employed with 854adult participants (mean age 34.52years) recruited from the USA via online crowdsourcing. Social anxiety was assessed using the Liebowitz Social Anxiety Scale (LSAS), and metacognitive beliefs were measured via the Metacognitions Questionnaire-30 (MCQ-30). Attentional bias was quantified using a computerized visual dot-probe paradigm, measuring reaction times in milliseconds. Following preprocessing and k-nearest neighbors imputation for missing values (approximately 2%), the data were split into an 80%training and 20%testing set. Supervised learning algorithms, including Random Forest, Support Vector Machines, and Gradient Boosting Regressors, were trained using 10-fold cross-validation. Model evaluation relied on R^2, Root Mean Square Error (RMSE), and Mean Absolute Error (MAE), while feature importance was interpreted using SHapley Additive exPlanations (SHAP) values. Findings: On the unseen testing set (n=171), the Gradient Boosting Regressor emerged as the optimal model, demonstrating superior predictive performance (R^2=.68, RMSE=13.65, MAE=10.42) compared to the Random Forest Regressor (R^2=.63, RMSE=14.68, MAE=11.55) and the Support Vector Machine (R^2=.55, RMSE=16.18, MAE=12.89). Feature importance analysis using SHAP values indicated that Negative Beliefs about uncontrollability and danger had the highest predictive influence (Mean ∣SHAP∣=6.84), closely followed by the Attentional Bias Score (Mean ∣SHAP∣=4.72) and the Need to Control thoughts (Mean ∣SHAP∣=3.55). Furthermore, SHAP dependence plots revealed a distinct non-linear interaction wherein the predictive impact of attentional bias was exponentially magnified in the presence of high negative metacognitive beliefs. Conclusion: Advanced machine learning algorithms successfully captured the complex architecture of social anxiety, demonstrating that clinical severity is predominantly driven by a synergistic, non-linear interaction between severe negative metacognitions and bottom-up visual hyper-vigilance toward threat.

Downloads

Download data is not yet available.

References

Abbasi, A., Aghaei Jeshvaghani, A., & Ebrahimi moghasam, H. (2020). Effectiveness of metacognition therapy on the anxiety and psychological wellbeing of the patients with generalized anxiety. medical journal of mashhad university of medical sciences, 63(5), 2745-2756. https://doi.org/10.22038/mjms.2021.17348

Asdolahzadeh, P., Sadeghi, J., & Abbasi Asfajir, A. A. (2021). Modeling the Structural Equations of Mode Metacognition with a Tendency to Cyberspace Mediated by Self-efficacy in Gifted Students [Research Article]. Iranian Journal of Educational Sociology, 4(2), 14-23. https://doi.org/10.52547/ijes.4.2.14

Aydın, S., Batmaz, S., & Aslan, E. A. (2025). Comparison of Cognitive Attentional Syndrome and Generic and Psychosis-Specific Metacognitive Beliefs in Remitted Patients with Schizophrenia, Schizoaffective Disorder, and Bipolar Disorder Type I with Psychotic Features with Healthy Controls. Journal of Rational-Emotive & Cognitive-Behavior Therapy, 43(2), 1-17. https://doi.org/10.1007/s10942-025-00586-1

Bagheri, A., Goodarzi, K., Rouzbehani, M., & Kakabraei, K. (2024). Comparing the effectiveness of metacognitive therapy, solution-focused therapy, and endurance exercises on self-efficacy beliefs in female students with social anxiety disorder. Journal of Psychological Science, 23(137), 133-153. https://psychologicalscience.ir/article-1-2420-en.html

Diop, S., Turmes, L., Specht, C., Seehagen, S., Juckel, G., & Mavrogiorgou, P. (2022). Capacities for meta-cognition, social cognition, and alexithymia in postpartum depression. Psychiatry research, 309, 114430. https://doi.org/10.1016/j.psychres.2022.114430

Esbjørn, B. H., Falch, A., Walczak, M., Normann, N., & Breinholst, S. (2020). Social Anxiety Disorder in Children: Investigating the Relative Contribution of Automatic Thoughts, Repetitive Negative Thinking and Metacognitions. Behavioural and Cognitive Psychotherapy, 49(2), 159-171. https://doi.org/10.1017/s1352465820000430

Ghaderi, B., Yazdanbakhsh, K., & Karami, J. (2022). Development and testing of a structural model of social anxiety based on maladaptive early schemas and metacognitive beliefs, with the mediating role of cognitive emotion regulation strategies in adolescent girls. Psychological Sciences Monthly, 21(109), 123-144. https://doi.org/10.52547/JPS.21.109.123

Hashemi, Z., Aini, S., & Shahjouei, T. (2022). Effectiveness of Metacognitive Therapy Based on Executive Function Training on Cognitive-Attentional Syndrome in Students with Social Anxiety. Clinical Psychology, 14(2), 1-11. http://edcbmj.ir/files/site1/user_files_944f39/zohreh-A-10-2348-4-3b83f2e.pdf

Hashemi, Z., Eyni, S., & Shahjoee, T. (2022). The Effectiveness of Metacognitive Therapy Brain-Based Executive Functioning

Training on Cognitive-Attention Syndrome in Students with Social Anxiety. Education Strategies in Medical Sciences, 15(2), 122-130. https://www.sid.ir/paper/1021490/en

Nateghi, N., Dadashi, M., & Mahmoud Alilou, M. (2019). Metacognitive Therapy in Improving sign, Metacognitive Beliefs and Thought Fusion in Patients with Obsessive-Compulsive Disorder [Original Research Article]. Middle Eastern Journal of Disability Studies­­­, 9(0), 112-112. http://jdisabilstud.org/article-1-991-en.html

Nematollahi, S., Afshari Nia, K., Alsadat Hosseini, S., Kakabraei, K., & Parandin, S. (2023). The Effectiveness of Metacognitive Therapy and Compassion-Based Therapy on Reducing Rumination, Anxiety and Worry in Obsessive-Compulsive Patients. Journal of Psychological Dynamics in Mood Disorders (PDMD), 2(3), 50-61. https://doi.org/10.22034/pdmd.2023.188277

Olivari, C., Mansueto, G., Marino, C., Candellari, G., Cericola, J., Binnie, J., & Caselli, G. (2025). Metacognitive beliefs and desire thinking as potential maintenance factors of compulsive sexual behavior. Addictive behaviors, 161, 108214. https://doi.org/10.1016/j.addbeh.2024.108214

Qarali, Z., & saberi, h. (2020). Relationship between Metacognition and Delusional Beliefs with Obsessive-Compulsive Symptoms. Thoughts and Behavior in Clinical Psychology, 15(56), 17-27. https://jtbcp.roudehen.iau.ir/article_1854_eb87d9ae095ceeaeb1c5afed396eaa56.pdf

Rabat Mili, S., & Karimi, M. (2018). The predictive role of metacognitive beliefs, mindfulness, and fear of negative evaluation in social anxiety among adolescents. Social Psychology Research, 8(31), 51-68. https://www.socialpsychology.ir/article_87485.html?lang=en

Rajabi, M. (2018). Comparing the effectiveness of metacognitive therapy, Acceptance and Commitment Therapy, and problem-solving therapy on the symptoms of social anxiety, quality of life, and feelings of loneliness Master's thesis in Psychology, Lorestan University].

Reshadat, S., Morovati, F., Zakiei, A., & Rajabi Gilan, N. (2019). Predicting social anxiety based on components of mindfulness, experiential avoidance, and metacognitive beliefs among adolescents. Journal of Mazandaran University of Medical Sciences, 29(176), 92-104. https://jmums.mazums.ac.ir/article-1-13162-en.html

Samia Shahani, S. S., Ahmadi, O., Nemati, A., & Hajizade Sanzighi, A. (2020). The mediating role of metacognitive beliefs in the relationship between the cognitive order of emotion and mindfulness. Applied Research in Consulting, 3(1), 83-103. https://www.jarci.ir/article_704282_bfae31d3c8978e5458e0dddf6fb89dc2.pdf

Strand, E. R., Nordahl, H., Hjemdal, O., & Nordahl, H. M. (2023). Metacognitive Beliefs Predict Interpersonal Problems in Patients With Social Anxiety Disorder. Scandinavian journal of psychology, 64(6), 819-824. https://doi.org/10.1111/sjop.12943

Williams, M., Honan, C., & Matthews, A. J. (2024). Attentional bias to threat: an investigation of psychological predictors beyond trait anxiety. Current Psychology. https://doi.org/10.1007/s12144-024-05641-1

Xu, Y., Zheng, P., Feng, W., Chen, L., Sun, S., Liu, J., Tang, W., Bao, C., Xu, L., Xu, D., & Zhao, K. (2023). Patterns of Attentional Bias in Antenatal Depression: An Eye-Tracking Study. Frontiers in Behavioral Neuroscience, 17. https://doi.org/10.3389/fnbeh.2023.1288616

Zhang, F., Huang, C. W., Yan, W., Ouyang, H., & Liu, W. (2024). Attentional Bias Modification and Attention Control Training in PTSD: A Systematic Review and Meta-Analysis. Therapeutic Advances in Psychopharmacology, 14. https://doi.org/10.1177/20451253241243260

Zhu, S., Zhao, Y., Lu, H., Guo, F., Lin, C., Qiu, H., & Jiang, K. (2024). Examining the Role of Negative Attentional Bias in Patients With Adolescent Depressive Disorders: An Emotion-Attention Blink Task Study. https://doi.org/10.21203/rs.3.rs-3865806/v1

Downloads

Additional Files

Published

2026-01-01

Submitted

2025-09-17

Revised

2025-12-14

Accepted

2025-12-19

How to Cite

Bosch Borras , J. ., Mett , Z. ., & Reynoso-Calderon , M. . (2026). Modeling Social Anxiety, Attentional Bias, and Metacognitive Beliefs with Supervised Learning Algorithms. Journal of Assessment and Research in Applied Counseling (JARAC), 8(1), 1-11. https://journals.kmanpub.com/index.php/jarac/article/view/5181