Decoding Demographic un-fairness from Indian Names

TL;DR

This paper investigates demographic classification from Indian names to understand biases and fairness issues, using datasets and classifiers to analyze gender and caste distinctions across regions.

Contribution

It introduces state-of-the-art classifiers trained on Indian datasets for gender and caste classification, with cross-dataset testing and bias analysis in the Indian context.

Findings

Models reveal regional variations in name-based demographic classification.

Cross-testing shows the robustness and limitations of classifiers across datasets.

Bias patterns in gender and caste classification are identified and analyzed.

Abstract

Demographic classification is essential in fairness assessment in recommender systems or in measuring unintended bias in online networks and voting systems. Important fields like education and politics, which often lay a foundation for the future of equality in society, need scrutiny to design policies that can better foster equality in resource distribution constrained by the unbalanced demographic distribution of people in the country. We collect three publicly available datasets to train state-of-the-art classifiers in the domain of gender and caste classification. We train the models in the Indian context, where the same name can have different styling conventions (Jolly Abraham/Kumar Abhishikta in one state may be written as Abraham Jolly/Abishikta Kumar in the other). Finally, we also perform cross-testing (training and testing on different datasets) to understand the efficacy of the above models. We also perform an error analysis of the prediction models. Finally, we attempt to assess the bias in the existing Indian system as case studies and find some intriguing patterns manifesting in the complex demographic layout of the sub-continent across the dimensions of gender and caste.