Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data
Learning Language and Multimodal Privacy-Preserving Markers of Mood from Mobile Data
复制标题
DOI：
10.18653/v1/2021.acl-long.322
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
P. Liang;Terrance Liu;Anna Cai;Michal Muszynski;Ryo Ishii;Nicholas Allen;R. Auerbach;D. Brent;R. Salakhutdinov;Louis-Philippe Morency
中科院分区：
文献类型：
--
作者：
P. Liang;Terrance Liu;Anna Cai;Michal Muszynski;Ryo Ishii;Nicholas Allen;R. Auerbach;D. Brent;R. Salakhutdinov;Louis-Philippe Morency
即使在普遍能够获得先进医疗服务的国家，精神健康状况仍然诊断不足。从容易收集的数据中准确有效地预测情绪的能力对心理健康障碍的早期检测，干预和治疗有几个重要的意义。一个有前途的数据源，以帮助监测人类行为是日常智能手机的使用。但是，必须注意在不通过个人（例如，个人可识别信息）或受保护（例如，种族、性别）属性。在本文中，我们研究了日常情绪的行为标记，使用最近的数据集移动的行为，从青少年人群的自杀行为的高风险。使用计算模型，我们发现移动的键入文本的语言和多模态表示（跨越键入的字符，单词，浏览时间和应用程序使用）可以预测日常情绪。然而，我们发现，经过训练以预测情绪的模型通常也会在其中间表示中捕获私人用户身份。为了解决这个问题，我们评估了在保持预测性的同时混淆用户身份的方法。通过将多模态表示与隐私保护学习相结合，我们能够推进性能隐私边界。
Mental health conditions remain underdiagnosed even in countries with common access to advanced medical care. The ability to accurately and efficiently predict mood from easily collectible data has several important implications for the early detection, intervention, and treatment of mental health disorders. One promising data source to help monitor human behavior is daily smartphone usage. However, care must be taken to summarize behaviors without identifying the user through personal (e.g., personally identifiable information) or protected (e.g., race, gender) attributes. In this paper, we study behavioral markers of daily mood using a recent dataset of mobile behaviors from adolescent populations at high risk of suicidal behaviors. Using computational models, we find that language and multimodal representations of mobile typed text (spanning typed characters, words, keystroke timings, and app usage) are predictive of daily mood. However, we find that models trained to predict mood often also capture private user identities in their intermediate representations. To tackle this problem, we evaluate approaches that obfuscate user identity while remaining predictive. By combining multimodal representations with privacy-preserving learning, we are able to push forward the performance-privacy frontier.