Psychiatrists diagnose mental disorders via the linguistic use of patients. Still, due to data privacy, existing passive mental health monitoring systems use alternative features such as activity, app usage, and location via mobile devices. We propose FedTherapist, a mobile mental health monitoring system that utilizes continuous speech and keyboard input in a privacy-preserving way via federated learning. We explore multiple model designs by comparing their performance and overhead for FedTherapist to overcome the complex nature of on-device language model training on smartphones. We further propose a Context-Aware Language Learning (CALL) methodology to effectively utilize smartphones' large and noisy text for mental health signal sensing. Our IRB-approved evaluation of the prediction of self-reported depression, stress, anxiety, and mood from 46 participants shows higher accuracy of FedTherapist compared with the performance with non-language features, achieving 0.15 AUROC improvement and 8.21% MAE reduction.

翻译：精神科医生通过患者的语言使用来诊断精神障碍。然而，由于数据隐私问题，现有的被动心理健康监测系统主要使用活动、应用使用和位置等替代特征。我们提出FedTherapist——一种通过联邦学习以隐私保护方式利用连续语音和键盘输入的移动心理健康监测系统。我们通过比较多种模型设计的性能和开销来探索FedTherapist的最佳方案，以克服智能手机上设备端语言模型训练的复杂性。我们进一步提出一种基于上下文感知的语言学习（CALL）方法，以有效利用智能手机中大量且嘈杂的文本进行心理健康信号感知。经IRB批准的实验评估中，我们针对46名参与者自报的抑郁、压力、焦虑和情绪状态进行预测，结果表明FedTherapist相比非语言特征的性能，实现了0.15的AUROC提升和8.21%的MAE降低，显示出更高的准确性。