The Association of Transformer-based Sentiment Analysis with Symptom Distress and Deterioration in Routine Psychotherapy Care
2026-05-11 • Computation and Language
Computation and LanguageMachine Learning
AI summaryⓘ
The authors studied how a new type of deep learning model, called a Transformer, can analyze emotions in therapy sessions by examining the words people use. They used this model to create scores that summarize the mood of therapy talks and compared these scores to a trusted mental health questionnaire called the OQ-45. They found that their sentiment scores matched well with parts of the questionnaire that measure feelings. Also, the scores helped distinguish patients who might be at risk of getting worse or dropping out of therapy. This suggests their method could be a helpful additional tool for tracking emotional health during therapy.
Sentiment analysisTransformer modelPsychotherapy sessionsOQ-45 instrumentEmotional valencePsychometricsClient distressDeterioration riskDeep learningNatural language processing
Authors
Douglas K. Faust, Peter Awad, Alexandre Vaz, Tony Rousmaniere
Abstract
Sentiment analysis has been of long-standing interest in psychotherapy research. Recently, the Transformer deep learning architecture has produced text-based sentiment analysis models that are highly accurate and context-aware. These models have been explored as proxies for emotion measurement instruments in psychotherapy, but not investigated as stand-alone psychometric tools. Using proposed utterance-level and session-level sentiment features derived from a fine-grained sentiment model on a large corpus of psychotherapy sessions (N = 751), we investigate the distribution of session aggregated sentiment scores. Further, we characterize the relationship of these features to individual components and the overall score of the OQ-45 instrument and find that this sentiment feature is most strongly correlated to components related to emotional valence in directionally intuitive ways. Finally, we report that there are statistically significant differences between the sentiment distributions for patients flagged as at risk of deterioration or dropping out of care via either the OQ Rational or Empirical outcome models. These correlations to a fully-validated psychometric instrument demonstrate that these proposed sentiment features are, at least, adjunctive measures of client distress and deterioration.