Detecting Social Influence in Event Cascades by Comparing Discriminative Rankers

2018/02/16 by Sandeep Soni, Soni, Sandeep, Shawn Ling Ramirez +3
Physics and Astronomy · Social Sciences · #Complex Network Analysis Techniques #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Misinformation and Its Impacts #Opinion Dynamics and Social Influence #Physics and Society (physics.soc-ph) #Social and Information Networks (cs.SI)

paper · pdf · doi:10.48550/arxiv.1802.06138

openalex publication_date 2018/02/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The global dynamics of event cascades are often governed by the local dynamics of peer influence. However, detecting social influence from observational data is challenging due to confounds like homophily and practical issues like missing data. We propose a simple discriminative method to detect influence from observational data. The core of the approach is to train a ranking algorithm to predict the source of the next event in a cascade, and compare its out-of-sample accuracy against a competitive baseline which lacks access to features corresponding to social influence. We analyze synthetically generated data to show that this method correctly identifies influence in the presence of confounds, and is robust to both missing data and misspecification --- unlike well-known alternatives. We apply the method to two real-world datasets: (1) the co-sponsorship of legislation in the U.S. House of Representatives on a social network of shared campaign donors; (2) rumors about the Higgs boson discovery on a follower network of 10⁵ Twitter accounts. Our model identifies the role of social influence in these scenarios and uses it to make more accurate predictions about the future trajectory of cascades.

Citations

• The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses
• Diffusion Models and Fashion: A Reassessment
• Homophily and Contagion Are Generically Confounded in Observational Social Network Studies
• Investigating Causal Relations by Econometric Models and Cross-spectral Methods
• Prediction and explanation in social systems
• Learning Hawkes Processes from Short Doubly-Censored Event Sequences
• Using Embeddings to Correct for Unobserved Confounding in Networks

Related

• Detecting Influence Campaigns in Social Networks Using the Ising Model
• Causal Influences over Social Learning Networks
• Learning hidden influences in large-scale dynamical social networks: A data-driven sparsity-based approach
• Causal Influences over Social Learning Networks
• Measuring Influence in Twitter Ecosystems using a Counting Process Modeling Framework