Analysis of non-typical emotions, such as stress, depression and engagement is less common and more complex compared to that of frequently discussed emotions like happiness, sadness, fear, and anger. The importance of these non-typical emotions has been increasingly recognized due to their implications on mental health and well-being. Stress and depression impact the engagement in daily tasks, highlighting the need to understand their interplay. This survey is the first to simultaneously explore computational methods for analyzing stress, depression, and engagement. We discuss the most commonly used datasets, input modalities, data processing techniques, and information fusion methods used for the computational analysis of stress, depression and engagement. A timeline and taxonomy of non-typical emotion analysis approaches along with their generic pipeline and categories are presented. Subsequently, we describe state-of-the-art computational approaches for non-typical emotion analysis, including a performance summary on the most commonly used datasets. Following this, we explore the applications, along with the associated challenges, limitations, and future research directions.

翻译：相较于常被讨论的快乐、悲伤、恐惧和愤怒等情绪，对压力、抑郁及投入度等非典型情绪的分析既不常见且更为复杂。由于这些非典型情绪对心理健康与福祉的影响，其重要性日益受到认可。压力与抑郁会影响日常任务中的投入程度，凸显了理解二者相互作用的必要性。本综述首次同时探讨了分析压力、抑郁及投入度的计算方法。我们讨论了用于压力、抑郁及投入度计算分析的最常用数据集、输入模态、数据处理技术及信息融合方法。本文呈现了非典型情绪分析方法的时间线、分类体系及其通用管线与类别。随后，我们描述了非典型情绪分析的前沿计算方法，包括在常用数据集上的性能总结。最后，我们探讨了相关应用、挑战、局限性及未来研究方向。