Estimating Online Influence Needs Causal Modeling! Counterfactual Analysis of Social Media Engagement
Preprint
Abstract
Understanding true influence in social media requires distinguishing correlation from causation--particularly when analyzing misinformation spread. While existing approaches focus on exposure metrics and network structures, they often fail to capture the causal mechanisms by which external temporal signals trigger engagement. We introduce a novel joint treatment-outcome framework that leverages existing sequential models to simultaneously adapt to both policy timing and engagement effects. Our approach adapts causal inference techniques from healthcare to estimate Average Treatment Effects (ATE) within the sequential nature of social media interactions, tackling challenges from external confounding signals. Through our experiments on real-world misinformation and disinformation datasets, we show that our models outperform existing benchmarks by 15--22% in predicting engagement across diverse counterfactual scenarios, including exposure adjustment, timing shifts, and varied intervention durations. Case studies on 492 social media users show our causal effect measure aligns strongly with the gold standard in influence estimation, the expert-based empirical influence.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Before It's Too Late: A State Space Model for the Early Prediction of Misinformation and Disinformation Engagement2025
- Empirically measuring online social influenceEPJ Data Science, 2024
- Association of Mobile Phone Location Data Indications of Travel and Stay-at-Home Mandates With COVID-19 Infection Rates in the USJAMA Network Open, 2020
- Using social and behavioural science to support COVID-19 pandemic responseNature Human Behaviour, 2020
- Experimental evidence for tipping points in social conventionScience, 2018
- Estimating peer effects in networks with peer encouragement designsProceedings of the National Academy of Sciences, 2016
- Exposure to ideologically diverse news and opinion on FacebookScience, 2015
- Social Influence Bias: A Randomized ExperimentScience, 2013
- Distinguishing influence-based contagion from homophily-driven diffusion in dynamic networksProceedings of the National Academy of Sciences, 2009
- A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effectMathematical Modelling, 1986