Balancing fairness and outcome in social network influence seeding
Decoupling Procedural and Outcome Fairness in Seed Allocation for Influence Maximization
Social and Information Networks
Summary
When groups get equal chances to start social campaigns online, the eventual impact can still be unfair because of how people influence each other. The authors found a way to separate the fairness of who gets chosen from the fairness of what results occur. They created a method that mixes giving groups set quotas with picking the most effective participants to raise a group's benefit while keeping results fairer. Tests on real and simulated social networks showed their method reduces unfairness without much loss in overall success.
What this means in practice
- •For online community managers: Allocate promotion or intervention resources to user groups to balance influence impact while reducing fairness gaps.
- •For social marketing teams: Design seed selection strategies that ensure equitable campaign outcomes across demographics with minimal loss in total reach.
Authors
Xiaojing Du, Chunlei Meng, Wentao Gao, Ke Sun, Feiyu Yang
Abstract
On online social platforms, equal seed access to interventions can yield unequal group outcomes through social spillovers, so an access audit alone can miss outcome disparities. We characterise this trade-off through an exact allocation-structure decomposition and a sharp first-moment floor for graph-independent seeding under additive spillovers on stochastic block networks. Decoupled Procedural Allocation (DPA) combines group quotas with selection by seeds' contributions to each group's outcome. Rankings balance total outcome against disparity, and within-quota exchanges reduce the gap. Computable bounds quantify retained total outcome. DPA achieves the smallest mean outcome gap among the compared methods at the common access tolerances on both development and prospective suites. Exposure and independent-cascade studies show how the propagation mechanism changes this trade-off. On Pokec, DPA nearly equalises modelled gender outcomes at the closest access-parity quota while preserving most of the degree-based allocation's total outcome.