Conductance and Influence-Capital: Modeling and Empirically Measuring Online Social Influence

Abstract

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. In a crisis like the COVID-19 pandemic, social influence can determine whether life-saving information is adopted, public health measures are observed, or immunization campaigns meet their targets. Existing literature studying online social influence suffers from several drawbacks. First, a disconnect appears between psychology approaches, which are generally performed and tested in controlled lab experiments, and the 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 (such as an ongoing pandemic); the latter often oversimplify the complexities of social influence and ignore psychosocial literature. This work begins to bridge this gap and presents three contributions towards modeling and empirically quantifying online influence. The first contribution is a data-driven Generalized Influence Model that incorporates two novel psychosocial-inspired mechanisms: the conductance of the diffusion network and the influence-capital distribution. The second contribution is a framework to empirically rank users' social influence using a human-in-the-loop method combined with crowdsourced pairwise influence comparisons. We build a human-labeled ground truth, calibrate our generalized influence model and perform a large-scale evaluation of influence. We find that our generalized model outperforms the current state-of-the-art approaches and corrects the inherent biases introduced by the widely used follower count. As the third contribution, we apply the influence model to discussions around COVID-19. We quantify users' influence and content veracity, tabulating it against their professions. We find that executives, media, and the military are more influential than pandemic-related experts such as life scientists and healthcare professionals. Worryingly, by leveraging existing COVID-19 misinformation datasets, we show that some of the most influential occupations also spread the most misinformation. These findings raise questions about the effectiveness of information dissemination by experts in situations of crisis.

Opinion Market Model: Stemming Far-Right Opinion Spread Using Positive Interventions

“…Our focus on the 2019-2020 Australian bushfires is motivated by the availability of human-annotated topics, opinions (Kong et al 2022) and stance classifiers (Ram et al 2022) trained on the same topic and timeframe. We use these classifiers to filter and label our dataset.…”

“…Bushfires are a normal summer occurrence in Australia. Furthermore, we deploy the far-right stance detector introduced by Ram et al (2022) -which leverages a textual homophily measurement to quantify the similarity between Twitter users and known far-right activists. On the Bushfire Opinions Twitter dataset, the stance detector achieves a 5fold CV AUC ROC score of 0.889.…”