Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions

  title={Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions},
  author={Zhuohao Chen and Nikolaos Flemotomos and Victor Ardulov and Torrey A. Creed and Zac E. Imel and David C. Atkins and Shrikanth S. Narayanan},
  journal={2021 43rd Annual International Conference of the IEEE Engineering in Medicine \& Biology Society (EMBC)},
Cognitive Behavioral Therapy (CBT) is a goal-oriented psychotherapy for mental health concerns implemented in a conversational setting. The quality of a CBT session is typically assessed by trained human raters who manually assign pre-defined session-level behavioral codes. In this paper, we develop an end-to-end pipeline that converts speech audio to diarized and transcribed text and extracts linguistic features to code the CBT sessions automatically. We investigate both word-level and… 

Figures and Tables from this paper

Automated quality assessment of cognitive behavioral therapy sessions through highly contextualized language representations

A BERT-based model is proposed for automatic behavioral scoring of a specific type of psychotherapy, called Cognitive Behavioral Therapy (CBT), where prior work is limited to frequency-based language features and/or short text excerpts which do not capture the unique elements involved in a spontaneous long conversational interaction.

Automated Detection of the Competency of Delivering Guided Self-Help for Anxiety via Speech and Language Processing

Speech and language play an essential role in automatically assessing several psychotherapeutic qualities. These automation procedures require translating the manual rating qualities to speech and

Local dynamic mode of Cognitive Behavioral Therapy

In order to increase mental health equity among the most vulnerable and marginalized communities, it is important to increase access to high-quality therapists. One facet of address these needs, is

"Am I A Good Therapist?" Automated Evaluation Of Psychotherapy Skills Using Speech And Language Technologies

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 is developed.

Multimodal Automatic Coding of Client Behavior in Motivational Interviewing

A neural network is developed to automatically detect MI codes using both the clients' and therapists' language and clients' voice, and the importance of semantic context in such detection is demonstrated, and machine learning models for predicting alcohol-use behavioral outcomes of clients are developed.



Language Features for Automated Evaluation of Cognitive Behavior Psychotherapy Sessions

This work examines how linguistic features can be effectively used to develop an automatic competency rating tool for CBT, and suggests that a real-world system could be developed to automatically evaluate CBT sessions to assist training, supervision, or quality assurance of services.

A dialog act tagging approach to behavioral coding: a case study of addiction counseling conversations

A computational approach to modeling and assessing the quality of MI sessions is examined and linear chain CRF models trained on coded session transcripts and Switchboard DAMSL dataset are used to predict utterance level behavioral codes as well as dialog acts.

Behavioral Coding of Therapist Language in Addiction Counseling Using Recurrent Neural Networks

A case study of modeling therapist language in addiction counseling, and an automatic coding approach to code therapist utterances with domain specific codes is presented.

Using Prosodic and Lexical Information for Learning Utterance-level Behaviors in Psychotherapy

It is demonstrated that prosodic features provide discriminative information relevant to the behavior task and show that they improve prediction when fused with automatically derived lexical features.

Multi-Label Multi-Task Deep Learning for Behavioral Coding

We propose a methodology for estimating human behaviors in psychotherapy sessions using multi-label and multi-task learning paradigms. We discuss the problem of behavioral coding in which data of

Scaling up the evaluation of psychotherapy: evaluating motivational interviewing fidelity via statistical text classification

Preliminary, encouraging findings are demonstrated regarding the utility of statistical text classification in bridging this methodological gap in replicating human-based judgments of provider fidelity in one specific psychotherapy— motivational interviewing (MI).

Preparing Clients for Cognitive Behavioral Therapy: A Randomized Pilot Study of Motivational Interviewing for Anxiety

Although CBT is a well-supported treatment for anxiety, recovery rates and compliance with treatment procedures are less than optimal. Using adjunctive brief preparatory interventions may help

Multimodal Interaction Modeling of Child Forensic Interviewing

Using a recently proposed definition of productivity, the dynamic systems modeling provides insight into the characteristics of interaction that are most relevant to effectively eliciting narrative and task-relevant information from a child.

Motivational Interviewing as an Adjunct to Cognitive Behavior Therapy for Anxiety Disorders: A Critical Review of the Literature.

Improving the Prediction of Therapist Behaviors in Addiction Counseling by Exploiting Class Confusions

This work addresses the problem of joint prosodic and lexical behavioral annotation for addiction counseling by proposing two implementations of hierarchical classification, which uses the behavior confusion matrix to cluster similar classes and makes the prediction based on a tree structure.