通过自发的面部表情表达情感是一种重要的非语言社交技巧。在我们的研究中,我们的目的是证明自闭症谱系障碍(ASD)儿童和ASD儿童的非ASD兄弟姐妹在这项技能方面都存在缺陷.
在这项研究中,我们分析了三个不同儿童群体的六个核心面部情绪表情-那些被诊断患有ASD(n=60),非ASD兄弟姐妹(n=60),和通常发育的儿童(n=60)。要分析面部表情,我们采用了一种计算机视觉程序,该程序使用机器学习算法来检测面部特征,并进行了一项基于证据的任务,该任务涉及评估参与者识别面部情绪表情的能力.
与通常发育的儿童相比,患有ASD的儿童和非ASD的兄弟姐妹表现出自发情绪表达的缺陷。有趣的是,在ASD组中,这些缺陷与自闭症症状的严重程度无关.
这项研究的结果表明,基于计算机的面部表情自动分析与上下文的社会场景任务具有测量限制的潜力,表达情绪的能力,它们补充了传统的社会表型行为缺陷的临床评估。这既适用于患有ASD的儿童,尤其是,给ASD儿童的非ASD兄弟姐妹。这项研究为以前的文献研究情感表达技巧增加了一种新颖的方法。
Expressing emotions through spontaneous facial expression is an important nonverbal social communication skill. In our
study, we aimed to demonstrate that both children with autism spectrum disorder (ASD) and the non-ASD siblings of children with ASD have deficits in this skill.
In this
study, we analyzed the six core facial emotion expressions of three distinct groups of children - those diagnosed with ASD (n = 60), non-ASD siblings (n = 60), and typically developed children (n = 60). To analyze facial expressions, we employed a computer vision program that uses machine learning algorithms to detect facial features and conducted an evidence-based task that involved assessing participants\' ability to recognize facial emotion expressions.
Deficits in spontaneous emotion expression were shown in the children with ASD and in non-ASD siblings when compared with typically developed children. Interestingly, it was determined that these deficits were not related to the severity of the autism symptoms in the ASD group.
The results of the
study suggest that computer-based automated analysis of facial expressions with contextual social scenes task holds potential for measuring limitations in the ability to express emotions, and they supplement the traditional clinical assessment of social phenotypical behavior deficits. This applies both to children with ASD and especially, to the non-ASD siblings of children with ASD. This
study adds a novel approach to previous literature examining the emotion expression skills.