DO CROWDS VALIDATE FALSE DATA? SYSTEMATIC DISTORTION AND AFFECTIVE POLARIZATION

• 成果类型: Article
• 署名作者: Pienta, Daniel A.; Somanchi, Sriram; Vishwamitra, Nishant; Berente, Nicholas; Thatcher, Jason Bennett
• 署名单位: University of Notre Dame; University of Texas System; University of Texas at San Antonio; University of Notre Dame; University of Colorado System; University of Colorado Boulder; University of Manchester; Alliance Manchester Business School
• 刊物名称: MIS QUARTERLY
• ISSN/ISSBN: 0276-7783
• DOI: 10.25300/MISQ/2024/17482
• 发表日期: 2025-03
• 页码: 347-366
• 关键词: Sociocognitive influences; SUBGROUPS; crowdsourcing; data validation; double debiased machine learning; political communication; EXPERIMENTAL VIGNETTE; data-collection; Social media; INFORMATION; BIAS; Loyalty; IDENTITY; betrayal; QUALITY

摘要

This research note examines how sociocognitive influences can systematically distort crowdsourced ground truth in event-centric data through subgroups. The wisdom of the crowd is based on the assumption that consensus drives accuracy. While existing research addresses the tendencies of the overall crowd, this research note shows that identifiable subgroups within the crowd can systematically influence crowdsource validation. We conducted an immersive experiment to investigate whether crowd consensus can be systematically distorted by subgroup-based sociocognitive influences, such as affective polarization. In the experiment, raters from a range of subgroups with varying levels of affective polarization were asked to view and validate crisis data from a violent public riot in the year 2020. Relying in part on double debiased machine learning techniques, we analyzed heterogeneous treatment effects across subgroups. The results show that affective polarization and more extreme raters, via the constructs of loyalty and betrayal, distort consensus-based ground truth in different ways. This research note demonstrates how subgroup-based sociocognitive influences can systematically distort the results of consensus-based crowdsourced validation. Additionally, it provides guidance for research and practice on how to account for identifiable subgroups in the crowd. These findings challenge key assumptions about the wisdom of crowds and the accuracy of crowdsourced ground truth in event-centric situations.