SeSaMe：一个用于模拟心理健康感知研究中自我报告真值的框架
SeSaMe: A Framework to Simulate Self-Reported Ground Truth for Mental Health Sensing Studies
AI总结：
SeSaMe框架利用预训练大型语言模型构建参与者心理模型，模拟心理量表上的自我报告回答，有效减轻数字心理健康研究中参与者的负担，且在多数场景下使用模拟数据训练机器学习模型的效果与真实数据相当。
摘要：
移动和可穿戴技术的进步使得被动监测个人的心理、行为和情感健康成为可能。这些方法通常依赖于纵向收集自我报告的结果（例如抑郁、压力和焦虑）来训练机器学习（ML）模型。然而，持续自我报告的需求给参与者增加了显著的负担，往往导致参与者流失、标签缺失或不认真的回答。在这项工作中，我们引入了使用心理模型的量表分数模拟（SeSaMe）框架，以减轻参与者在数字心理健康研究中的负担。通过利用预训练的大型语言模型（LLMs），SeSaMe 能够模拟参与者在心理量表上的回答。在 SeSaMe 中，研究人员可以通过向 LLMs 提供有关参与者内在行为倾向的信息，使 LLMs 构建参与者的心理模型，从而模拟他们在心理量表上的回答。我们展示了 SeSaMe 的一个应用，其中我们使用 GPT-4，将来自另一个量表的回答作为行为信息，来模拟在一个量表上的回答。我们还评估了人类与 SeSaMe 模拟的心理量表回答之间的一致性。然后，我们通过复制先前研究中的既定抑郁和焦虑筛查任务，进行了实验以检验 SeSaMe 模拟的回答作为训练 ML 模型真值的效用。我们的结果表明 SeSaMe 是一种很有前景的方法，但其一致性可能因量表和特定预测目标而异。我们还观察到，在大多数评估场景中，使用模拟数据训练的模型性能与使用真实数据训练相当。最后，我们讨论了 SeSaMe 在解决研究人员在被动感知研究中收集真值所面临的一些挑战方面的潜在影响。
英文摘要：
Advances in mobile and wearable technologies have enabled the potential to passively monitor a person's mental, behavioral, and affective health. These approaches typically rely on longitudinal collection of self-reported outcomes, e.g., depression, stress, and anxiety, to train machine learning (ML) models. However, the need to continuously self-report adds a significant burden on the participants, often resulting in attrition, missing labels, or insincere responses. In this work, we introduce the Scale Scores Simulation using Mental Models (SeSaMe) framework to alleviate participants' burden in digital mental health studies. By leveraging pre-trained large language models (LLMs), SeSaMe enables the simulation of participants' responses on psychological scales. In SeSaMe, researchers can prompt LLMs with information on participants' internal behavioral dispositions, enabling LLMs to construct mental models of participants to simulate their responses on psychological scales. We demonstrate an application of SeSaMe, where we use GPT-4 to simulate responses on one scale using responses from another as behavioral information. We also evaluate the alignment between human and SeSaMe-simulated responses to psychological scales. Then, we present experiments to inspect the utility of SeSaMe-simulated responses as ground truth in training ML models by replicating established depression and anxiety screening tasks from a previous study. Our results indicate SeSaMe to be a promising approach, but its alignment may vary across scales and specific prediction objectives. We also observed that model performance with simulated data was on par with using the real data for training in most evaluation scenarios. We conclude by discussing the potential implications of SeSaMe in addressing some challenges researchers face with ground-truth collection in passive sensing studies.
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。
