Redefining Research Crowdsourcing: Incorporating Human Feedback with LLM-Powered Digital Twins

TL;DR

This paper introduces a hybrid digital twin framework that models crowd workers to improve research data quality and worker engagement amidst AI automation challenges.

Contribution

It proposes a novel use of personalized AI digital twins to emulate human worker behavior, maintaining authenticity while enhancing productivity.

Findings

Digital twins can improve productivity and reduce decision fatigue.

The system maintains response quality comparable to human responses.

Transparency and ethical considerations are crucial for adoption.

Abstract

Crowd work platforms like Amazon Mechanical Turk and Prolific are vital for research, yet workers' growing use of generative AI tools poses challenges. Researchers face compromised data validity as AI responses replace authentic human behavior, while workers risk diminished roles as AI automates tasks. To address this, we propose a hybrid framework using digital twins, personalized AI models that emulate workers' behaviors and preferences while keeping humans in the loop. We evaluate our system with an experiment (n=88 crowd workers) and in-depth interviews with crowd workers (n=5) and social science researchers (n=4). Our results suggest that digital twins may enhance productivity and reduce decision fatigue while maintaining response quality. Both researchers and workers emphasized the importance of transparency, ethical data use, and worker agency. By automating repetitive tasks and preserving human engagement for nuanced ones, digital twins may help balance scalability with authenticity.