用深度语言模型分析对话，预测抑郁焦虑，准确率超85%。
Depression and Anxiety Prediction Using Deep Language Models and Transfer Learning
- 基于用户对话数据训练语言模型，结合迁移学习进行情绪状态识别。
- 二分类任务AUC达0.86（抑郁）至0.79（焦虑共病），表现稳定。
- 发现抑郁比焦虑更依赖词汇序列线索，适合临床辅助筛查场景。
数字筛查与监测应用可辅助行为健康诊疗。本研究利用深度语言模型，从16,000次用户与应用的对话交互中检测抑郁、焦虑及其共病情况，标签来源于应用内收集的PHQ-8和GAD-7结果。结果显示，二分类任务的AUC在0.86（抑郁）至0.79（焦虑共病）之间，当用户同时存在或均无两种症状时表现最佳，且该现象非由数据偏差导致。此外，证据表明抑郁的判断更依赖于词汇序列特征，而焦虑则相对弱相关。
原文摘要 · Abstract (English)
Digital screening and monitoring applications can aid providers in the management of behavioral health conditions. We explore deep language models for detecting depression, anxiety, and their co-occurrence from conversational speech collected during 16k user interactions with an application. Labels come from PHQ-8 and GAD-7 results also collected by the application. We find that results for binary classification range from 0.86 to 0.79 AUC, depending on condition and co-occurrence. Best performance is achieved when a user has either both or neither condition, and we show that this result is not attributable to data skew. Finally, we find evidence suggesting that underlying word sequence cues may be more salient for depression than for anxiety.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。