Context-Dependent Autonomic Responses in Social Anxiety During Cognitive-Emotional Stress

Social anxiety disorder (SAD) is associated with heightened physiological arousal during socially evaluative situations, yet it remains unclear whether similar autonomic responses emerge during non-evaluative cognitive-emotional stress. This study investigated wearable electrodermal activity (EDA) responses in socially anxious (SA) and non-socially anxious (NSA) individuals during an emotionally salient 2-back working memory task involving facial expressions. Fifty participants (25 SA, 25 NSA) completed a resting-state baseline and task condition while EDA signals were acquired using a Shimmer3 GSR+ sensor. EDA features spanning tonic, phasic, sympathetic, spectral, and nonlinear domains were analyzed using mixed ANOVAs and complementary machine learning models. Results showed significant increases in autonomic arousal during task engagement across all participants, confirming that the task induced substantial sympathetic activation. However, no consistent between-group differences were observed, with only transient interaction effects emerging during the initial task phase. Machine learning analysis demonstrated above-chance discrimination between SA and NSA individuals using resting-state EDA (average AUC~=~0.73), whereas classification performance during task engagement declined to near-chance levels (average AUC~$\leq$~0.57). These findings suggest that cognitively demanding emotional tasks, in the absence of explicit social-evaluative threat, elicit comparable autonomic responses regardless of social anxiety status and may obscure subtle resting-state physiological differences between groups. More broadly, our findings highlight the context-dependent nature of wearable autonomic biomarkers for anxiety assessment and digital mental health monitoring. With this manuscript, we release both the code and data publicly.