Support Vector Machine Classification of Cyberchondria Severity Based on Health Anxiety, Intolerance of Uncertainty, and Online Reassurance Seeking
Journal of Assessment and Research in Applied Counseling · 2026 · 8 (3) · 1-15
DOI: 10.61838/kman.jarac.5822 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Assessment and Research in Applied Counseling, 2026. Verfasst von Yodit Betru und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Objective
The present study aimed to classify cyberchondria severity based on health anxiety, intolerance of uncertainty, and online reassurance seeking using a Support Vector Machine model among adults living in Canada. Methods and Materials: This applied, quantitative, cross-sectional study was conducted using a predictive machine-learning classification design. The statistical population included adults living in Canada who used the Internet to search for health-related information. A total of 426 participants were selected through online convenience sampling. Data were collected using the Cyberchondria Severity Scale-12, the Short Health Anxiety Inventory, the Intolerance of Uncertainty Scale-12, an online reassurance-seeking measure, and a demographic information form. Cyberchondria severity was classified into low, moderate, and high groups using percentile-based categorization. The dataset was divided into training and testing subsets using stratified sampling, with 70% of the data used for model training and 30% reserved for independent testing. Support Vector Machine models with different kernels were trained and compared through cross-validation, and the final model was evaluated using accuracy, precision, recall, F1-score, area under the curve, and confusion matrix analysis.
Findings
The radial basis function Support Vector Machine showed the best cross-validated performance and was selected as the final model. In the independent test set, the final model achieved an overall accuracy of 0.84, macro F1-score of 0.84, weighted F1-score of 0.84, and macro AUC of 0.92. Class-level results showed strong performance for low cyberchondria severity and high cyberchondria severity, with F1-scores of 0.87 and 0.89, respectively. The moderate severity group showed lower but acceptable classification performance, with an F1-score of 0.76. The confusion matrix indicated that classification errors occurred mainly between adjacent severity categories, with no direct confusion between low and high severity groups. Permutation-based importance analysis indicated that online reassurance seeking was the strongest predictor, followed by health anxiety and intolerance of uncertainty.
Conclusion
The findings showed that cyberchondria severity can be accurately classified using a Support Vector Machine model based on health anxiety, intolerance of uncertainty, and online reassurance seeking. The results highlight the importance of anxiety-related cognition, difficulty tolerating health uncertainty, and repeated digital reassurance seeking in identifying individuals at greater risk for severe cyberchondria.
Zitieren
APA
Betru, Y., Petrovic, J., Sabillano, A., & McKenzie, J. (2026). Support Vector Machine Classification of Cyberchondria Severity Based on Health Anxiety, Intolerance of Uncertainty, and Online Reassurance Seeking. Journal of Assessment and Research in Applied Counseling, 8(3), 1-15. https://doi.org/10.61838/kman.jarac.5822
Vancouver
Betru Y, Petrovic J, Sabillano A, McKenzie J. Support Vector Machine Classification of Cyberchondria Severity Based on Health Anxiety, Intolerance of Uncertainty, and Online Reassurance Seeking. Journal of Assessment and Research in Applied Counseling. 2026;8(3):1-15. doi:10.61838/kman.jarac.5822
BibTeX
@article{Betru2026,
author = {Betru, Yodit and Petrovic, Jelena and Sabillano, Anna and McKenzie, Jodi},
title = {Support Vector Machine Classification of Cyberchondria Severity Based on Health Anxiety, Intolerance of Uncertainty, and Online Reassurance Seeking},
journal = {Journal of Assessment and Research in Applied Counseling},
year = {2026},
volume = {8},
number = {3},
pages = {1--15},
doi = {10.61838/kman.jarac.5822}
}
EUVIMED