With the growing prevalence of psychological interventions, it is vital to have measures which rate the effectiveness of psychological care to assist in training, supervision, and quality assurance of services. Traditionally, quality assessment is addressed by human raters who evaluate recorded sessions along specific dimensions, often codified through constructs relevant to the approach and domain. This is, however, a cost-prohibitive and time-consuming method that leads to poor feasibility and limited use in real-world settings. To facilitate this process, we have developed an automated competency rating tool able to process the raw recorded audio of a session, analyzing who spoke when, what they said, and how the health professional used language to provide therapy. Focusing on a use case of a specific type of psychotherapy called "motivational interviewing", our system gives comprehensive feedback to the therapist, including information about the dynamics of the session (e.g., therapist's vs. client's talking time), low-level psychological language descriptors (e.g., type of questions asked), as well as other high-level behavioral constructs (e.g., the extent to which the therapist understands the clients' perspective). We describe our platform and its performance using a dataset of more than 5000 recordings drawn from its deployment in a real-world clinical setting used to assist training of new therapists. Widespread use of automated psychotherapy rating tools may augment experts' capabilities by providing an avenue for more effective training and skill improvement, eventually leading to more positive clinical outcomes.

In this paper, we present an approach for predicting utterance level behaviors in psychotherapy sessions using both speech and lexical features. We train long short term memory (LSTM) networks with an attention mechanism using words, both manually and automatically transcribed, and prosodic features, at the word level, to predict the annotated behaviors. We demonstrate that prosodic features provide discriminative information relevant to the behavior task and show that they improve prediction when fused with automatically derived lexical features. Additionally, we investigate the weights of the attention mechanism to determine words and prosodic patterns which are of importance to the behavior prediction task.

No abstract

Social exclusion has many effects on individuals, including the increased need to belong and elevated sensitivity to social information. Using a self-reporting method, and an eye-tracking technique, this study explored people’s need to belong and attentional bias towards the socio-emotional information (pictures of positive and negative facial expressions compared to those of emotionally-neutral expressions) after experiencing a brief episode of social exclusion. We found that: (1) socially-excluded individuals reported higher negative emotions, lower positive emotions, and stronger need to belong than those who were not socially excluded; (2) compared to a control condition, social exclusion caused a longer response time to probe dots after viewing positive or negative face images; (3) social exclusion resulted in a higher frequency ratio of first attentional fixation on both positive and negative emotional facial pictures (but not on the neutral pictures) than the control condition; (4) in the social exclusion condition, participants showed shorter first fixation latency and longer first fixation duration to positive pictures than neutral ones but this effect was not observed for negative pictures; (5) participants who experienced social exclusion also showed longer gazing duration on the positive pictures than those who did not; although group differences also existed for the negative pictures, the gaze duration bias from both groups showed no difference from chance. This study demonstrated the emotional response to social exclusion as well as characterising multiple eye-movement indicators of attentional bias after experiencing social exclusion.

No abstract