Estimating Social Influence from Observational Data

TL;DR

This paper introduces Poisson Influence Factorization (PIF), a novel method to estimate social influence from observational data by addressing confounding factors, and demonstrates its effectiveness on real and semi-synthetic datasets.

Contribution

The paper formalizes social influence as a causal effect, develops PIF for estimating it from observational data, and establishes conditions for its accurate recovery.

Findings

PIF outperforms related methods in estimating social influence.

PIF remains robust under certain violations of assumptions.

Empirical results on Last.fm data validate PIF's effectiveness.

Abstract

We consider the problem of estimating social influence, the effect that a person's behavior has on the future behavior of their peers. The key challenge is that shared behavior between friends could be equally explained by influence or by two other confounding factors: 1) latent traits that caused people to both become friends and engage in the behavior, and 2) latent preferences for the behavior. This paper addresses the challenges of estimating social influence with three contributions. First, we formalize social influence as a causal effect, one which requires inferences about hypothetical interventions. Second, we develop Poisson Influence Factorization (PIF), a method for estimating social influence from observational data. PIF fits probabilistic factor models to networks and behavior data to infer variables that serve as substitutes for the confounding latent traits. Third, we develop assumptions under which PIF recovers estimates of social influence. We empirically study PIF with semi-synthetic and real data from Last.fm, and conduct a sensitivity analysis. We find that PIF estimates social influence most accurately compared to related methods and remains robust under some violations of its assumptions.