Data from: Wide range screening of algorithmic bias in word embedding models using large sentiment lexicons reveals underreported bias types

Concerns about gender bias in word embedding models have captured substantial attention in the algorithmic bias research literature. Other bias types however have received lesser amounts of scrutiny. This work describes a large-scale analysis of sentiment associations in popular word embedding models along the lines of gender and ethnicity but also along the less frequently studied dimensions of socioeconomic status, age, physical appearance, sexual orientation, religious sentiment and political leanings. Consistent with previous scholarly literature, this work has found systemic bias against given names popular among African-Americans in most embedding models examined. Gender bias in embedding models however appears to be multifaceted and often reversed in polarity to what has been regularly reported. Interestingly, using the common operationalization of the term bias in the fairness literature, novel types of so far unreported bias types in word embedding models have also been identified. Specifically, the popular embedding models analyzed here display negative biases against middle and working-class socioeconomic status, male children, senior citizens, plain physical appearance and intellectual phenomena such as Islamic religious faith, non-religiosity and conservative political orientation. Reasons for the paradoxical underreporting of these bias types in the relevant literature are probably manifold but widely held blind spots when searching for algorithmic bias and a lack of widespread technical jargon to unambiguously describe a variety of algorithmic associations could conceivably be playing a role. The causal origins for the multiplicity of loaded associations attached to distinct demographic groups within embedding models are often unclear but the heterogeneity of said associations and their potential multifactorial roots raises doubts about the validity of grouping them all under the umbrella term bias. Richer and more fine-grained terminology as well as a more comprehensive exploration of the bias landscape could help the fairness epistemic community to characterize and neutralize algorithmic discrimination more efficiently.

词嵌入模型（word embedding models）中的性别偏见问题，在算法偏见（algorithmic bias）研究领域已引发广泛关注。但其他类型的偏见却鲜有得到充分审视。本研究对主流词嵌入模型中的情感关联开展了大规模分析，不仅覆盖性别与族裔维度，还涵盖了此前较少被研究的社会经济地位、年龄、外貌、性取向、宗教倾向以及政治立场等维度。与此前学术文献的结论一致，本研究在多数被分析的词嵌入模型中，发现了针对非裔美国人常用名字的系统性偏见。然而，词嵌入模型中的性别偏见呈现出多面性，其极性往往与学界常规报道的结论相悖。有趣的是，采用公平性研究领域中通用的偏见操作化定义（operationalization），本研究还识别出了词嵌入模型中此前从未被报道过的新型偏见类型。具体而言，本次分析的主流词嵌入模型，对以下群体与属性表现出负面偏见：中产阶级与工薪阶层的社会经济地位、男性儿童、老年群体、普通外貌，以及伊斯兰宗教信仰、无宗教信仰与保守派政治立场这类认知相关属性。这类偏见类型在相关文献中被反常地报道不足的原因可能是多方面的：学界在搜索算法偏见时普遍存在认知盲区，同时缺乏能够清晰描述各类算法关联的通用技术术语，这两点或均可成为潜在诱因。词嵌入模型中附着于不同人口群体的大量带有偏见倾向的关联，其因果成因往往尚不明确；而这类关联的异质性，以及其潜在的多因素根源，也让将其全部归入‘偏见’这一总括性术语的合理性受到质疑。采用更丰富、更细粒度的术语体系，同时对偏见图景开展更全面的探索，将有助于公平性研究学界更高效地刻画算法歧视并加以消解。