Leveraging the Power of AI and Social Interactions to Restore Trust in Public Polls
Amr Akmal Abouelmagd, Amr Hilal
TL;DR
This paper tackles the credibility challenges of crowdsourced polling conducted over social networks by proposing a decentralized, AI-enabled approach that leverages social dissemination patterns. It constructs a dissemination graph from how poll requests spread through a network and applies Graph Neural Networks to node-embedding features to detect ineligible participation without centralized eligibility verification. Evaluations on two real-world datasets demonstrate strong predictive performance, with higher accuracy when more root nodes (credible spreaders) are present and varying results across graph structures. The work suggests a scalable, privacy-conscious path to restore trust in large-scale, participatory polling with practical implications for broader, more reliable public data collection.
Abstract
The emergence of crowdsourced data has significantly reshaped social science, enabling extensive exploration of collective human actions, viewpoints, and societal dynamics. However, ensuring safe, fair, and reliable participation remains a persistent challenge. Traditional polling methods have seen a notable decline in engagement over recent decades, raising concerns about the credibility of collected data. Meanwhile, social and peer-to-peer networks have become increasingly widespread, but data from these platforms can suffer from credibility issues due to fraudulent or ineligible participation. In this paper, we explore how social interactions can help restore credibility in crowdsourced data collected over social networks. We present an empirical study to detect ineligible participation in a polling task through AI-based graph analysis of social interactions among imperfect participants composed of honest and dishonest actors. Our approach focuses solely on the structure of social interaction graphs, without relying on the content being shared. We simulate different levels and types of dishonest behavior among participants who attempt to propagate the task within their social networks. We conduct experiments on real-world social network datasets, using different eligibility criteria and modeling diverse participation patterns. Although structural differences in social interaction graphs introduce some performance variability, our study achieves promising results in detecting ineligibility across diverse social and behavioral profiles, with accuracy exceeding 90% in some configurations.