Automatic Multimodal Affect Detection for Research and Clinical Use

项目摘要 一种可靠有效的自动化系统，用于量化具有生态重要性的人类情感行为 自然主义环境将成为研究和临床实践的变革性工具。使用NIMH 支持(MH R01-096951)，我们朝着这一目标取得了根本性进展。在建议的项目中，我们 扩展当前情感行为自动多模式测量的能力(视觉、听觉和 口头)开发和验证一个自动系统，用于检测积极、攻击性和 烦躁不安的行为和成分较低层次的情感行为和言语内容。该系统基于 家庭环境中的手工生活编码系统已产生与以下方面相关的关键发现 抑郁症和其他障碍的发展精神病理学和人际过程。两种模式 将会被开发出来。其中一个将使用理论上派生的特征，这些特征是由先前的行为学研究得出的 科学和情感计算；其他由深度学习提供信息的经验派生特征。这个 模型将在1300多个不同的二进制和三进制交互任务数据库中进行培训 来自美国和澳大利亚的青少年和成人参与者。 手动编码的系统间可靠性将使用k-折交叉验证进行评估 和会话级摘要分数。模型之间的差异以及与参与者因素的关系将是 使用一般线性模型进行了检验。为了确保通用性，我们将进一步训练和测试 独立的数据库也是如此。为了评估自动编码的结构效度，我们将使用 三个数据库中可用的有效性数据，以确定自动编码是否实现相同或 关于抑郁症风险和发展的更好的发现模式。以下程序已在 共享数据库和软件工具的地方，我们将设计供非专业人员使用的自动化系统 并使其可用于研究和临床使用。实现这些目标将提供行为科学 拥有强大的工具来研究情绪、精神病理学和人际关系过程中的基本问题； 临床医生提高评估和跟踪临床和人际功能随时间的变化的能力。 相关性 对于行为科学，从多模式(视觉、听觉和语言)自动编码情感行为 INPUT将为研究人员提供强大的工具来检查情绪、精神病理学、 和人际关系的过程。对于临床使用，自动测量将帮助临床医生评估 各种疾病的脆弱性和保护性因素以及对治疗的反应。更广泛地说， 自动化测量将有助于智能教师在教育、社会培训方面的进步 咨询方面的技能和说服力，以及更广泛的情感计算。

Project Summary A reliable and valid automated system for quantifying human affective behavior in ecologically important naturalistic environments would be a transformational tool for research and clinical practice. With NIMH support (MH R01-096951), we have made fundamental progress toward this goal. In the proposed project, we extend current capabilities in automated multimodal measurement of affective behavior (visual, acoustic, and verbal) to develop and validate an automated system for detecting the constructs of Positive, Aggressive, and Dysphoric behavior and component lower-level affective behaviors and verbal content. The system is based on the manual Living in Family Environments Coding System that has yielded critical findings related to developmental psychopathology and interpersonal processes in depression and other disorders. Two models will be developed. One will use theoretically-derived features informed by previous research in behavioral science and affective computing; the other empirically derived features informed by Deep Learning. The models will be trained in three separate databases of dyadic and triadic interaction tasks from over 1300 adolescent and adult participants from the US and Australia. Intersystem reliability with manual coding will be evaluated using k-fold cross-validation for both momentary and session level summary scores. Differences between models and in relation to participant factors will be tested using the general linear model. To ensure generalizability, we further will train and test between independent databases as well. To evaluate construct validity of automated coding, we will use the ample validity data available in the three databases to determine whether automated coding achieves the same or better pattern of findings with respect to depression risk and development. Following procedures already in place for sharing databases and software tools, we will design the automated systems for use by non-specialists and make them available for research and clinical use. Achieving these goals will provide behavioral science with powerful tools to examine basic questions in emotion, psychopathology, and interpersonal processes; and clinicians to improve assessment and ability to track change in clinical and interpersonal functioning over time. Relevance For behavioral science, automated coding of affective behavior from multimodal (visual, acoustic, and verbal) input will provide researchers with powerful tools to examine basic questions in emotion, psychopathology, and interpersonal processes. For clinical use, automated measurement will help clinicians to assess vulnerability and protective factors and response to treatment for a wide range of disorders. More generally, automated measurement would contribute to advances in intelligent tutors in education, training in social skills and persuasion in counseling, and affective computing more broadly.