Supervised Speaker Diarization Using Random Forests: A Tool for Psychotherapy Process Research

Development of Supervised Speaker Diarization System Based on the PyAnnote Audio Processing Library

Diarization is an important task when work with audiodata is executed, as it provides a solution to the problem related to the need of dividing one analyzed call recording into several speech recordings, each of which belongs to one speaker. Diarization systems segment audio recordings by defining the time boundaries of utterances, and typically use unsupervised methods to group utterances belonging to individual speakers, but do not answer the question "who is speaking?" On the other hand, there are biometric systems that identify individuals on the basis of their voices, but such systems are designed with the prerequisite that only one speaker is present in the analyzed audio recording. However, some applications involve the need to identify multiple speakers that interact freely in an audio recording. This paper proposes two architectures of speaker identification systems based on a combination of diarization and identification methods, which operate on the basis of segment-level or group-level classification. The open-source PyAnnote framework was used to develop the system. The performance of the speaker identification system was verified through the application of the AMI Corpus open-source audio database, which contains 100 h of annotated and transcribed audio and video data. The research method consisted of four experiments to select the best-performing supervised diarization algorithms on the basis of PyAnnote. The first experiment was designed to investigate how the selection of the distance function between vector embedding affects the reliability of identification of a speaker's utterance in a segment-level classification architecture. The second experiment examines the architecture of cluster-centroid (group-level) classification, i.e., the selection of the best clustering and classification methods. The third experiment investigates the impact of different segmentation algorithms on the accuracy of identifying speaker utterances, and the fourth examines embedding window sizes. Experimental results demonstrated that the group-level approach offered better identification results were compared to the segment-level approach, and the latter had the advantage of real-time processing.

Withdrawal ruptures in adolescents with borderline personality disorder psychotherapy are marked by increased speech pauses-can minimal responses be automatically detected?

Alliance ruptures of the withdrawal type are prevalent in adolescents with borderline personality disorder (BPD). Longer speech pauses are negatively perceived by these patients. Safran and Muran's rupture model is promising but its application is very work intensive. This workload makes research costly and limits clinical usage. We hypothesised that pauses can be used to automatically detect one of the markers of the rupture model i.e. the minimal response marker. Additionally, the association of withdrawal ruptures with pauses was investigated. A total of 516 ruptures occurring in 242 psychotherapy sessions collected in 22 psychotherapies of adolescent patients with BPD and subthreshold BPD were investigated. Trained observers detected ruptures based on video and audio recordings. In contrast, pauses were automatically marked in the audio-recordings of the psychotherapy sessions and automatic speaker diarisation was used to determine the speaker-switching patterns in which the pauses occur. A random forest classifier detected time frames in which ruptures with the minimal response marker occurred based on the quantity of pauses. Performance was very good with an area under the ROC curve of 0.89. Pauses which were both preceded and followed by therapist speech were the most important predictors for minimal response ruptures. Research costs can be reduced by using machine learning techniques instead of manual rating for rupture detection. In combination with other video and audio derived features like movement analysis or automatic facial emotion detection, more complete rupture detection might be possible in the future. These innovative machine learning techniques help to narrow down the mechanisms of change of psychotherapy, here specifically of the therapeutic alliance. They might also be used to technologically augment psychotherapy training and supervision.

The Influence of Cognitive Biases and Financial Factors on Forecast Accuracy of Analysts

The objective of this study was to jointly analyze the importance of cognitive and financial factors in the accuracy of profit forecasting by analysts. Data from publicly traded Brazilian companies in 2019 were obtained. We used text analysis to assess the cognitive biases from the qualitative reports of analysts. Further, we analyzed the data using statistical regression learning methods and statistical classification learning methods, such as Multiple Linear Regression (MRL), k-dependence Bayesian (k-DB), and Random Forest (RF). The Bayesian inference and classification methods allow an expansion of the research line, especially in the area of machine learning, which can benefit from the examples of factors addressed in this research. The results indicated that, among cognitive biases, optimism had a negative relationship with forecasting accuracy while anchoring bias had a positive relationship. Commonality, to a lesser extent, also had a positive relationship with the analyst's accuracy. Among financial factors, the most important aspects in the accuracy of analysts were volatility, indebtedness, and profitability. Age of the company, fair value, American Depositary Receipts (ADRs), performance, and loss were still important but on a smaller scale. The results of the RF models showed a greater explanatory power. This research sheds light on the cognitive as well as financial aspects that influence the analyst's accuracy, jointly using text analysis and machine learning methods, capable of improving the explanatory power of predictive models, together with the use of training models followed by testing.

Alliance Ruptures and Resolutions in Personality Disorders

PURPOSE OF REVIEW

This review provides an overview of the state of research on alliance ruptures and resolutions in the treatment of personality disorders (PDs). We discuss frequently used instruments to measure alliance ruptures and resolutions. We discuss the effectiveness of rupture resolution processes and highlight possible avenues for research to explore. Innovative assessments with the potential to reveal the link of ruptures and resolutions and mechanisms of psychotherapeutic change are discussed.

RECENT FINDINGS

The assessment of alliance rupture and resolutions is heterogeneous. Instruments vary largely with respect to a direct or indirect assessment, the time resolution of assessment (integral therapy, phase, session, event), session sampling strategy and perspectives (patient, therapist, observer). The heterogeneity in the instruments and study designs impedes comparability and interpretation of the findings. Results support the hypothesis that ruptures are more frequent in PD. Results also point towards beneficial effects of rupture resolution patterns, early alliance quality, and resolution complexity. Few studies control findings for pretreatment factors. Evidence points to the direction that rupture resolution processes can be considered a general principle of change in the treatment of PD. The concept of alliance ruptures and resolutions provides a useful tool for the management of the therapeutic alliance and its moments of deteriorations throughout the treatment course. Dimensional pretreatment personality functioning is considered a key variable in future studies to highlight what works for whom.