PNAS2014-01-08 5:00 AM

Private traits and attributes are predictable from digital records of human behavior 私人特质和属性可以通过人类行为的数据记录来预测

Abstract
We show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of highly sensitive personal attributes including: sexual orientation, ethnicity, religious and political views, personality traits, intelligence, happiness, use of addictive substances, parental separation, age, and gender. The analysis presented is based on a dataset of over 58,000 volunteers who provided their Facebook Likes, detailed demographic profiles, and the results of several psychometric tests. The proposed model uses dimensionality reduction for preprocessing the Likes data, which are then entered into logistic/linear regression to predict individual psychodemographic profiles from Likes. The model correctly discriminates between homosexual and heterosexual men in 88% of cases, African Americans and Caucasian Americans in 95% of cases, and between Democrat and Republican in 85% of cases. For the personality trait “Openness,” prediction accuracy is close to the test–retest accuracy of a standard personality test. We give examples of associations between attributes and Likes and discuss implications for online personalization and privacy. 论文摘要 我们表示可以轻易查询的习惯和Facebook喜好的数字记录可用于自动准确地预测一系列高灵敏度的个人属性,其中包括:性取向,种族,宗教和政治观点,人格特质,智商,幸福,成瘾事物的使用,父母离异,年龄和性别。在此所示的分析基于超过58,000名志愿者的数据集,这些志愿者提供了他们的Facebook喜好,详细的人口统计特征,以及几种心理测试的结果。该提供的模型采用降维来预处理有关喜好的数据,随后这些数据被输入进逻辑/线性回归模型中,从喜好中来预测个体的心理人口统计特征。该模型能准确地鉴别88%的同性恋和异性恋男子实例,95 %的非裔美国人和白人美国人实例,以及85%的民主党和共和党实例。该模型 对于“开放”的人格特质的预测准确度十分接近标准性格测试的重测精度。我们给出了属性与喜好之间关联的例子,且讨论了它对在线个性化和隐私性的意义。

KEYWORDS

SHARE & LIKE

COMMENTS

ABOUT THE AUTHOR

PNAS

0 Following 4 Fans 0 Projects 58 Articles

SIMILAR ARTICLES

AbstractIn animal communication research, vocal labeling refers to incidents in which an animal consistently uses a specific acoustic signal when prese

Read More

AbstractWe show that easily accessible digital records of behavior, Facebook Likes, can be used to automatically and accurately predict a range of high

Read More

意义2010年 墨西哥湾北部深水地平线(MC252)灾难泄漏了超过400万桶原油。石油从海底架上升到了有许多大型中上层鱼类产卵的表层。在此我们描述了现场采集油样对包括蓝鳍金枪鱼,黄鳍金枪鱼和琥珀鱼在内的温水掠食动物迅速发育胚胎的影响。对于每个物种,环境相关MC252原油泄漏造成了心脏发育的严重缺陷。此

Read More

Abstract In the last decade there has been an exponential increase in knowledge about the genetic basis of complex human traits, including neuropsychi

Read More

AbstractGold mining has rapidly increased in western Amazonia, but the rates and ecological impacts of mining remain poorly known and potentially under

Read More

Abstract The interrelationships between hydrologically driven evolution of legacy landscapes downstream of major mining districts and the contaminatio

Read More

Abstract Changes in global (ocean and land) precipitation are among the most important and least well-understood consequences of climate change. Incre

Read More

AbstractAntiangiogenic therapy has shown clear activity and improved survival benefit for certain tumor types. However, an incomplete understanding of

Read More

AbstractThe biological mechanisms underlying long-term partner bonds in humans are unclear. The evolutionarily conserved neuropeptide oxytocin (OXT) is

Read More

Abstract Wine grapes present a unique biogeography model, wherein microbial biodiversity patterns across viticultural zones not only answer questions

Read More