Lalk Christopher, Targan Kim, Steinbrenner Tobias, Schaffrath Jana, Eberhardt Steffen, Schwartz Brian, Vehlen Antonia, Lutz Wolfgang, Rubel Julian
Department of Psychology, Osnabrück University, Osnabrück, Germany.
Department of Psychology, University of Trier, Trier, Germany.
Front Psychiatry. 2025 May 9;16:1504306. doi: 10.3389/fpsyt.2025.1504306. eCollection 2025.
In the context of psychotherapy, emotions play an important role both through their association with symptom severity, as well as their effects on the therapeutic relationship. In this analysis, we aim to train a large language model (LLM) for the detection of emotions in German speech. We want to apply this model on a corpus of psychotherapy transcripts to predict symptom severity and alliance aiming to identify the most important emotions for the prediction of symptom severity and therapeutic alliance.
We employed a public labeled dataset of 28 emotions and translated the dataset into German. A pre-trained LLM was then fine-tuned on this dataset for emotion classification. We applied the fine-tuned model to a dataset containing 553 psychotherapy sessions of 124 patients. Using machine learning (ML) and explainable artificial intelligence (AI), we predicted symptom severity and alliance by the detected emotions.
Our fine-tuned model achieved modest classification performance ( =0.45, =0.41, =0.42) across the 28 emotions. Incorporating all emotions, our ML model showed satisfying performance for the prediction of symptom severity ( = .50; 95%-CI:.42,.57) and moderate performance for the prediction of alliance scores ( = .20; 95%-CI:.06,.32). The most important emotions for the prediction of symptom severity were , and . The most important emotions for the prediction of alliance were , and .
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.
在心理治疗中，情绪通过与症状严重程度的关联以及对治疗关系的影响发挥着重要作用。在本分析中，我们旨在训练一个用于检测德语语音中情绪的大语言模型（LLM）。我们希望将此模型应用于心理治疗转录本语料库，以预测症状严重程度和治疗联盟，旨在识别预测症状严重程度和治疗联盟最重要的情绪。
我们使用了一个包含28种情绪的公开标记数据集，并将该数据集翻译成德语。然后在这个数据集上对预训练的LLM进行微调以进行情绪分类。我们将微调后的模型应用于包含124名患者的553次心理治疗会话的数据集。使用机器学习（ML）和可解释人工智能（AI），我们通过检测到的情绪预测症状严重程度和治疗联盟。
我们的微调模型在28种情绪上取得了中等分类性能（=0.45，=0.41，=0.42）。纳入所有情绪后，我们的ML模型在预测症状严重程度方面表现出令人满意的性能（=0.50；95%置信区间：0.42，0.57），在预测联盟得分方面表现出中等性能（=0.20；95%置信区间：0.06，0.32）。预测症状严重程度最重要的情绪是 ， 和 。预测联盟最重要的情绪是 ， 和 。
尽管分类结果仅为中等，但我们的模型尤其在预测症状严重程度方面取得了良好性能。结果证实了负面情绪在预测症状严重程度中的作用，同时也突出了积极情绪在促进良好联盟中的作用。未来的方向包括改进标记数据集，特别是在领域特异性和纳入上下文信息方面。此外，可以整合其他模态和基于自然语言处理（NLP）的联盟评估。
