Kern Margaret L, Eichstaedt Johannes C, Schwartz H Andrew, Dziurzynski Lukasz, Ungar Lyle H, Stillwell David J, Kosinski Michal, Ramones Stephanie M, Seligman Martin E P
University of Pennsylvania, Philadelphia, PA, USA
University of Pennsylvania, Philadelphia, PA, USA.
Assessment. 2014 Apr;21(2):158-69. doi: 10.1177/1073191113514104. Epub 2013 Dec 8.
We present a new open language analysis approach that identifies and visually summarizes the dominant naturally occurring words and phrases that most distinguished each Big Five personality trait.
Using millions of posts from 69,792 Facebook users, we examined the correlation of personality traits with online word usage. Our analysis method consists of feature extraction, correlational analysis, and visualization.
The distinguishing words and phrases were face valid and provide insight into processes that underlie the Big Five traits.
Open-ended data driven exploration of large datasets combined with established psychological theory and measures offers new tools to further understand the human psyche.
我们提出一种新的开放式语言分析方法，该方法可识别并直观总结出最能区分每种大五人格特质的主要自然出现的单词和短语。
我们使用来自69792名Facebook用户的数百万条帖子，研究了人格特质与在线词汇使用之间的相关性。我们的分析方法包括特征提取、相关性分析和可视化。
这些具有区分性的单词和短语表面效度良好，并能深入了解大五人格特质背后的过程。
结合既定的心理学理论和测量方法，对大型数据集进行开放式数据驱动探索，为进一步理解人类心理提供了新工具。
