Modeling Human Perspectives with Socio-Demographic Representations

TL;DR

This paper introduces Socio-Contrastive Learning, a novel method that models annotator perspectives by integrating socio-demographic attributes with textual data, improving prediction and analysis of subjective viewpoints in NLP.

Contribution

It presents a new approach that jointly learns socio-demographic and textual representations, outperforming traditional methods and enabling better understanding of human perspective variation.

Findings

Outperforms standard concatenation-based methods in predicting perspectives.

Provides effective analysis and visualization of demographic influences.

Enhances understanding of subjective annotation disagreements.

Abstract

Humans often hold different perspectives on the same issues. In many NLP tasks, annotation disagreement can reflect valid subjective perspectives. Modeling annotator perspectives and understanding their relationship with other human factors, such as socio-demographic attributes, have received increasing attention. Prior work typically focuses on single demographic factors or limited combinations. However, in real-world settings, annotator perspectives are shaped by complex social contexts, and finer-grained socio-demographic attributes can better explain human perspectives. In this work, we propose Socio-Contrastive Learning, a method that jointly models annotator perspectives while learning socio-demographic representations. Our method provides an effective approach for the fusion of socio-demographic features and textual representations to predict annotator perspectives, outperforming standard concatenation-based methods. The learned representations further enable analysis and visualization of how demographic factors relate to variation in annotator perspectives. Our code is available at GitHub: https://github.com/Leixin-Zhang/Socio_Contrastive_Learning