arXiv 2501.086962025-01-15cs.CL

基于深度学习的特征融合用于中国心理援助热线的情绪分析与自杀风险区分

Deep Learning-Based Feature Fusion for Emotion Analysis and Suicide Risk Differentiation in Chinese Psychological Support Hotlines

School of Software Engineering, Beijing University of Technology（北京工业大学软件学院）；Peking University Huilongguan Clinical Medical School（北京大学回龙湖临床医学院）；Sorbonne Université（索邦大学）；Institut du Cerveau – Paris Brain Institute - ICM（巴黎脑研究所（ICM））；CNRS（法国国家科学研究中心）；Inria（法国国家信息与自动化研究所）；Inserm（法国国家健康与医学研究院）；AP-HP（巴黎公共医疗集团）；Hôpital de la Pitié-Salpêtrière（皮蒂-萨尔皮特里医院）

Han Wang, Jianqiang Li, Qing Zhao, Zhonglong Chen, Changwei Song, Jing Tang, Yuning Huang, Wei Zhai, Yongsheng Tong, Guanghui Fu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本研究提出基频声学特征与深度学习特征融合的情绪分析方法，在热线数据和公开数据集上取得优异表现，发现情绪波动特征可辅助自杀风险预测，为心理评估和自杀预防提供新方向。

摘要：

心理健康是一项至关重要的全球公共卫生问题，心理援助热线在提供心理健康援助及早期识别自杀风险方面发挥着关键作用。然而，当前研究对这些通话中传递的情绪表达仍探索不足。本研究提出一种将基频声学特征与基于深度学习的特征相结合的方法，用于分析和理解热线互动中表达的情绪。利用中国最大心理援助热线的数据集，我们的方法在负性情绪二分类任务上取得了79.13%的F1值。此外，该方法还在一个公开数据集上进行了多类情绪分类验证，表现出优于当前最优方法的性能。为探究其临床相关性，我们将该模型用于分析对话中的负性情绪频率和情绪变化率，对比了46名有自杀行为的受试者与无自杀行为的受试者。尽管自杀组的情绪变化频率高于非自杀组，但差异无统计学意义。重要的是，我们的研究结果表明，情绪波动强度和频率可作为心理评估量表和自杀风险预测的新特征。该方法为情绪动态研究提供了宝贵见解，通过与临床工具和评估相结合，有望推动早期干预并完善自杀预防策略。源代码公开于https://github.com/Sco-field/Speechemotionrecognition/tree/main。

英文摘要：

Mental health is a critical global public health issue, and psychological support hotlines play a pivotal role in providing mental health assistance and identifying suicide risks at an early stage. However, the emotional expressions conveyed during these calls remain underexplored in current research. This study introduces a method that combines pitch acoustic features with deep learning-based features to analyze and understand emotions expressed during hotline interactions. Using data from China's largest psychological support hotline, our method achieved an F1-score of 79.13% for negative binary emotion classification.Additionally, the proposed approach was validated on an open dataset for multi-class emotion classification,where it demonstrated better performance compared to the state-of-the-art methods. To explore its clinical relevance, we applied the model to analysis the frequency of negative emotions and the rate of emotional change in the conversation, comparing 46 subjects with suicidal behavior to those without. While the suicidal group exhibited more frequent emotional changes than the non-suicidal group, the difference was not statistically significant.Importantly, our findings suggest that emotional fluctuation intensity and frequency could serve as novel features for psychological assessment scales and suicide risk prediction.The proposed method provides valuable insights into emotional dynamics and has the potential to advance early intervention and improve suicide prevention strategies through integration with clinical tools and assessments The source code is publicly available at https://github.com/Sco-field/Speechemotionrecognition/tree/main.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。