Towards a Holistic Approach: Understanding Sociodemographic Biases in NLP Models using an Interdisciplinary Lens

TL;DR

This paper advocates for an interdisciplinary approach to understanding sociodemographic biases in NLP models, addressing current limitations in scope, focus, and methodology to better assess societal impacts.

Contribution

It introduces a comprehensive framework that broadens bias analysis in NLP by incorporating sociological and interdisciplinary perspectives beyond traditional model-centric methods.

Findings

Highlights gaps in sociodemographic bias research

Proposes an interdisciplinary framework for bias analysis

Calls for broader societal impact assessments

Abstract

The rapid growth in the usage and applications of Natural Language Processing (NLP) in various sociotechnical solutions has highlighted the need for a comprehensive understanding of bias and its impact on society. While research on bias in NLP has expanded, several challenges persist that require attention. These include the limited focus on sociodemographic biases beyond race and gender, the narrow scope of analysis predominantly centered on models, and the technocentric implementation approaches. This paper addresses these challenges and advocates for a more interdisciplinary approach to understanding bias in NLP. The work is structured into three facets, each exploring a specific aspect of bias in NLP.