Empirically measuring online social influence

Social influence pervades our everyday lives and lays the foundation for complex social phenomena, such as the spread of misinformation and the polarization of communities. A disconnect appears between psychology approaches, generally performed and tested in controlled lab experiments, and quantitative methods, which are usually data-driven and rely on network and event analysis. The former are slow, expensive to deploy, and typically do not generalize well to topical issues; the latter often oversimplify the complexities of social influence and ignore psychosocial literature. This work bridges this gap by introducing a human-in-the-loop active learning method that empirically quantifies social influence by crowdsourcing pairwise influence comparisons. We develop simulation and fitting tools, allowing us to estimate the required budget based on the design features and the worker’s decision accuracy. We perform a series of pilot studies to quantify the impact of design features on worker accuracy. We deploy our method to estimate the influence ranking of 500 X/Twitter users. We validate our measure by showing that the obtained empirical influence is tightly linked with agency and communion, the Big Two of social cognition, with agency being the most important dimension for influence formation.