The semantic representation of prejudice and stereotypes
The semantic representation of prejudice and stereotypes
复制标题
DOI：
10.1016/j.cognition.2017.03.016
复制
发表时间：
2017-07-01
期刊：
影响因子：
3.4
通讯作者：
Bhatia, Sudeep
中科院分区：
文献类型：
--
作者：
Bhatia, Sudeep
我们使用语义表征理论来研究偏见和刻板印象。特别是，我们考虑了在美国发表的报纸文章的大型数据集，并将潜在语义分析(LSA)--一种重要的人类语义记忆模型--应用于这些数据集，以学习常见的男性和女性、白人、非裔美国人和拉丁裔名字的表示。LSA对单词分布统计数据进行奇异值分解，以恢复单词向量表示，我们发现恢复的表示显示了使用隐含联想测试等任务在人类参与者中观察到的偏差类型。重要的是，对于中等维度的矢量表示，这些偏差最强，而对于维度很高或很低的表示，这些偏差会减弱或消失。中等维度的LSA模型在学习种族、民族和基于性别的类别方面也是最好的，这表明通过对单词分布统计进行降维而获得的社会类别知识可以促进偏见和刻板印象的联系。(C)2017爱思唯尔B.V.保留所有权利。
We use a theory of semantic representation to study prejudice and stereotyping. Particularly, we consider large datasets of newspaper articles published in the United States, and apply latent semantic analysis (LSA), a prominent model of human semantic memory, to these datasets to learn representations for common male and female, White, African American, and Latino names. LSA performs a singular value decomposition on word distribution statistics in order to recover word vector representations, and we find that our recovered representations display the types of biases observed in human participants using tasks such as the implicit association test. Importantly, these biases are strongest for vector representations with moderate dimensionality, and weaken or disappear for representations with very high or very low dimensionality. Moderate dimensional LSA models are also the best at learning race, ethnicity, and gender-based categories, suggesting that social category knowledge, acquired through dimensionality reduction on word distribution statistics, can facilitate prejudiced and stereotyped associations. (C) 2017 Elsevier B.V. All rights reserved.