No abstract

Although social anxiety and depression are common, they are often underdiagnosed and undertreated, in part due to difficulties identifying and accessing individuals in need of services. Current assessments rely on client self-report and clinician judgment, which are vulnerable to social desirability and other subjective biases. Identifying objective, nonburdensome markers of these mental health problems, such as features of speech, could help advance assessment, prevention, and treatment approaches. Prior research examining speech detection methods has focused on fully supervised learning approaches employing strongly labeled data. However, strong labeling of individuals high in symptoms or state affect in speech audio data is impractical, in part because it is not possible to identify with high confidence which regions of a long speech indicate the person’s symptoms or affective state. We propose a weakly supervised learning framework for detecting social anxiety and depression from long audio clips. Specifically, we present a novel feature modeling technique named NN2Vec that identifies and exploits the inherent relationship between speakers’ vocal states and symptoms/affective states. Detecting speakers high in social anxiety or depression symptoms using NN2Vec features achieves F-1 scores 17% and 13% higher than those of the best available baselines. In addition, we present a new multiple instance learning adaptation of a BLSTM classifier, named BLSTM-MIL. Our novel framework of using NN2Vec features with the BLSTM-MIL classifier achieves F-1 scores of 90.1% and 85.44% in detecting speakers high in social anxiety and depression symptoms.

Prospection, the mental simulation of future events, has been theoretically linked to physical and mental health. Prior studies have found that prospection is malleable; however, no research to our knowledge has tested whether a scalable intervention explicitly targeting the simulation of positive future outcomes can lead to more generalized positive prospection, and enhance positive outlook and reduce distress. The current study tested a novel, web-based cognitive bias modification for interpretation (CBM-I) program designed to shift prospective bias towards more positive (as opposed to negative) representations of future outcomes among 172 participants selected for having a relatively negative baseline expectancy bias. Results showed that following CBM-I, participants in active training conditions exhibited more positive expectations about the future, and increased self-efficacy and growth mindset. Also, optimism increased and depression and anxiety symptoms decreased following active training, but this also occurred for the control condition. Analyses did not suggest that changes in positive expectations mediated changes in positive outlook outcomes. Results suggest that an online prospection intervention can lead to more positive expectations about future events and improve positive outlook, though open questions remain about what accounts for the training effects.

Dialectical Behavior Therapy (DBT) is effective at treating disorders of emotion dysregulation. However, it is unclear which mechanisms contribute to these effects. The aim of this study was to characterize the within-person associations of two theoretically relevant mechanisims of change, skill use and skill effectiveness, with anxiety, stress, and depression. Participants (n = 19, Mage = 31.8, 68% female) with a primary anxiety or depressive disorder completed daily reports (N = 1344) of DBT skill use, perceived effectiveness, anxiety, stress, and depression during a 16-session DBT skills training group. DBT skill use increased across treatment, p < .01, but effectiveness did not, p = .64. Within persons, participants used more skills on days with greater stress and anxiety, p < .01, which predicted next-day decreases in stress and anxiety, p = .03. On days when participants reported higher effectiveness, they used more skills than their personal average when experiencing more intense negative affect, p < .01. These results suggest using more skills, especially when used more effectively, is a mechanism by which DBT skills groups address emotional dysfunction for those with transdiagnostic emotional disorders.

No abstract