Detecting Demographic Bias in Automatically Generated Personas

Detecting Demographic Bias in Automatically Generated Personas
复制标题

检测自动生成的角色中的人口统计偏差

DOI:
--
复制
发表时间:
2019
期刊:
CHI Extended Abstracts
影响因子:
--
通讯作者:
B. Jansen
B. Jansen
中科院分区:
--
文献类型:
--
作者:
Joni O. Salminen;Soon;B. Jansen

文献摘要

被引文献

相似文献

我们通过从YouTube Analytics数据中生成人物角色来调查自动生成人物角色中人口统计学偏差的存在。尽管该方法具有预期的客观性,但我们在数据驱动的人物角色中发现了偏见的因素。在进行精确匹配比较时,偏差最大,在年龄或性别水平上进行比较时,偏差减小。当生成的人物角色数量增加时,这种偏差也会减少。例如,人物角色的数量较少导致女性人物角色的代表性不足。这表明,更多的角色可以更平衡地代表用户群体,而更少的角色则会增加偏见。开发数据驱动的人物角色的研究人员和实践者应该通过将人物角色与潜在的原始数据进行比较,考虑在他们的人物角色中存在算法偏差的可能性,即使是无意的。
We investigate the existence of demographic bias in automatically generated personas by producing personas from YouTube Analytics data. Despite the intended objectivity of the methodology, we find elements of bias in the data-driven personas. The bias is highest when doing an exact match comparison, and the bias decreases when comparing at age or gender level. The bias also decreases when increasing the number of generated personas. For example, the smaller number of personas resulted in underrepresentation of female personas. This suggests that a higher number of personas gives a more balanced representation of the user population and a smaller number increases biases. Researchers and practitioners developing data-driven personas should consider the possibility of algorithmic bias, even unintentional, in their personas by comparing the personas against the underlying raw data.