Employing large language models for emotion detection in psychotherapy transcripts
Bibliographic Data
| ID | 15520534 |
|---|---|
| Authors | Christopher Lalk (0000-0002-1793-3507, Osnabrück University, corresponding author), Kim Targan (Osnabrück University), Tobias Steinbrenner (0009-0005-0434-2870, Osnabrück University), Jana Schaffrath (0000-0003-0106-0243, Universität Trier), Steffen T Eberhardt (0000-0002-9900-4671, Universität Trier), Steffen Eberhardt, Brian Schwartz (0000-0003-4695-4953, Universität Trier), Antonia Vehlen (0000-0002-6019-3161, Universität Trier), Wolfgang Lutz (0000-0001-7975-8145, Universität Trier), Julian A Rubel (0000-0002-9625-6611, Osnabrück University), Julian Rubel |
| Year | 2025 |
| Volume | 16 |
| Pages | 1504306-1504306 |
| Publication date | 2025-05-09 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Frontiers in Psychiatry (JOURNAL) |
| Journal identifiers | ISSN: 1664-0640 • E-ISSN: 1664-0640 |
| Publisher | Frontiers Media (PUBLISHER • CH) |
| DOI | 10.3389/fpsyt.2025.1504306 |
| PMID | 40417271 |
| OpenAlex | W4410247794 |
| Language | EN |
| References cited | 85 |
Even though the classification results were only moderate, our model achieved a good performance especially for prediction of symptom severity. The results confirm the role of negative emotions in the prediction of symptom severity, while they also highlight the role of positive emotions in fostering a good alliance. Future directions entail the improvement of the labeled dataset, especially with regards to domain-specificity and incorporating context information. Additionally, other modalities and Natural Language Processsing (NLP)-based alliance assessment could be integrated
Alliance · Anger · Context (archaeology · German · Psychotherapist · Surprise · Clinical Psychology · Mental Health Research Topics · Mental Health via Writing · Personality Disorders and Psychopathology · Psychology · Social Psychology
Applied Multiple Regression/Correlation Analysis for the Behavioral Sciences
Regularization and Variable Selection Via the Elastic Net
Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance
Distinctions between emotion and mood
Super Learner
Facial Action Coding System
The generalizability of the psychoanalytic concept of the working alliance.
Support-Vector Networks
Tripartite model of anxiety and depression
Emotion Dysregulation Model of Mood and Anxiety Disorders
Relation between Emotion Regulation and Mental Health
The alliance in adult psychotherapy
Emotion regulation and mental health
Opinion Mining and Sentiment Analysis
Emotion regulation and mental health.
Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature
The broaden–and–build theory of positive emotions
The Brief Symptom Inventory
Random Forests
A Brief Measure for Assessing Generalized Anxiety Disorder
Regression Shrinkage and Selection Via the Lasso
The Measurement of Observer Agreement for Categorical Data
The PHQ-9
A Value for n-Person Games
Development and validation of brief measures of positive and negative affect
Use Omega Rather than Cronbach’s Alpha for Estimating Reliability. But
At what sample size do correlations stabilize
Bad is Stronger than Good
An argument for basic emotions
The Psychological Meaning of Words
| Citation velocity | historical |
|---|---|
| Highly cited | No |