Darling or Babygirl ? Investigating Stylistic Bias in Sentiment Analysis
Darling or Babygirl ? Investigating Stylistic Bias in Sentiment Analysis
复制标题
亲爱的还是宝贝女儿？
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Alexander M. Rush
中科院分区：
文献类型：
--
作者：
J. Shen;Lauren Fratamico;Iyad Rahwan;Alexander M. Rush
情感分析越来越多地用于从客户服务到意见挖掘的一系列应用。当不同群体生成的文本表达相同的底层内容时，就会出现风格偏见。使用三种词汇对齐技术，我们发现标准情感模型对文体上主要不同的词对产生了显著不同的情感得分。我们建议一种简单的对齐和替代方法来自动生成黑箱模型中潜在不良偏差的示例，以便更好地促进基于风格变化的差异处理的识别和缓解。
Sentiment analysis is increasingly used for a range of applications from customer service to opinion mining. Stylistic bias arises when text generated by different groups of people expressing the same underlying content receive disparate treatment. Using three lexical alignment techniques, we find that standard sentiment models produce signifi-cantly different sentiment scores for word pairs that mainly differ stylistically. We suggest a simple align and substitute method to automatically generate examples of potentially undesirable biases in black-box models in order to better facilitate identification and mitigation of differential treatment based on stylistic variation.