Semantic Mapping Reveals Distinct Patterns in Descriptions of Social Relations in Adults with Autism Spectrum Disorder
Semantic Mapping Reveals Distinct Patterns in Descriptions of Social Relations in Adults with Autism Spectrum Disorder
复制标题
DOI：
10.1002/aur.1581
复制
发表时间：
2016-08-01
期刊：
影响因子：
4.7
通讯作者：
Gerber, Andrew J.
中科院分区：
文献类型：
--
作者：
Luo, Sean X.;Shinall, Jacqueline A.;Gerber, Andrew J.
与典型的成年人相比，患有自闭症谱系障碍（ASD）的成年人可能会以不同的方式描述其他人。在这项研究中，我们首先要求参与者用10个积极和10个消极的特征来描述与父母和亲密朋友等密切相关的人。然后，我们使用标准的自然语言处理方法来描述和可视化这些描述。这些描述性句子的复杂模式表现出个体与ASD和对照参与者之间的语义空间的差异。机器学习算法能够自动检测和区分这两组。此外，我们发现，这些描述性的句子，从成人自闭症患者表现出较少的连接所定义的词-词共现的描述，这些连接的话形成了一个不那么“小世界”的网络。(C)2015年国际自闭症研究学会，Wiley Periodicals，Inc。
Adults with autism spectrum disorder (ASD) may describe other individuals differently compared with typical adults. In this study, we first asked participants to describe closely related individuals such as parents and close friends with 10 positive and 10 negative characteristics. We then used standard natural language processing methods to digitize and visualize these descriptions. The complex patterns of these descriptive sentences exhibited a difference in semantic space between individuals with ASD and control participants. Machine learning algorithms were able to automatically detect and discriminate between these two groups. Furthermore, we showed that these descriptive sentences from adults with ASD exhibited fewer connections as defined by word-word co-occurrences in descriptions, and these connections in words formed a less "small-world" like network. (C) 2015 International Society for Autism Research, Wiley Periodicals, Inc.