While the potential of Artificial Intelligence (AI)—particularly Natural Language Processing (NLP) models—for detecting symptoms of depression from text has been vastly researched, only a few studies examine such potential for the detection of social anxiety symptoms. We investigated the ability of the large language model (LLM) GPT-4 to correctly infer social anxiety symptom strength from transcripts obtained from semi-structured interviews. N = 51 adult participants were recruited from a convenience sample of the German population. Participants filled in a self-report questionnaire on social anxiety symptoms (SPIN) prior to being interviewed on a secure online teleconference platform. Transcripts from these interviews were then evaluated by GPT-4. GPT-4 predictions were highly correlated (r = 0.79) with scores obtained on the social anxiety self-report measure. Following the cut-off conventions for this population, an F₁ accuracy score of 0.84 could be obtained. Future research should examine whether these findings hold true in larger and more diverse datasets.

Social anxiety is both highly prevalent and debilitating, with dysfunctional beliefs playing a crucial role in its persistence. This randomized controlled trial examined whether a remote avatar-based intervention for restructuring dysfunctional beliefs was associated with changes in social anxiety symptoms in a sample with subclinical social anxiety disorder (SAD). Data from N = 235 participants who completed all study stages were included in the analyses. While participants in the intervention group were tasked with contradicting their personal dysfunctional beliefs verbalized by the avatar, participants in the control group contradicted nonsense statements uttered by the avatar. Three sessions took place over three consecutive days. Data collection occurred pre-, post-intervention, and at a 14-days-follow-up. A significant group x time interaction effect ( F (1, 233) = 4.106, p < .05) indicates a stronger SAD symptom reduction within the intervention group in comparison to the control group. Post-hoc analysis revealed a medium effect size for symptom reduction in the intervention group ( d = 0.57) and a small effect size for the control group ( d = 0.34). An additional linear multiple regression analysis identified that increased self-esteem ( B = − 0.56, p < .001) was associated with reductions in SAD symptoms. An increase in dysfunctional social phobia cognitions was associated with an increase in SAD symptoms ( B = 0.175, p = .021). Avatar-based cognitive restructuring was associated with reductions in SAD symptoms in a subclinical sample. Changes in self-esteem and social phobia-related cognitions were also associated with symptom changes, but causal relationships cannot be inferred from this study design.

In this paper, a novel method for reducing the runtime complexity of a support vector machine classifier is presented. The new training algorithm is fast and simple. This is achieved by an over-complete wavelet transform that finds the optimal approximation of the support vectors. The presented derivation shows that the wavelet theory provides an upper bound on the distance between the decision function of the support vector machine and our classifier. The obtained classifier is fast, since a Haar wavelet approximation of the support vectors is used, enabling efficient integral image-based kernel evaluations. This provides a set of cascaded classifiers of increasing complexity for an early rejection of vectors easy to discriminate. This excellent runtime performance is achieved by using a hierarchical evaluation over the number of incorporated and additional over the approximation accuracy of the reduced set vectors. Here, this algorithm is applied to the problem of face detection, but it can also be used for other image-based classifications. The algorithm presented, provides a 530-fold speedup over the support vector machine, enabling face detection at more than 25 fps on a standard PC.