On Influencing the Influential: Disparity Seeding

Online social network platforms have become a crucial medium to disseminate the latest political, commercial, and social information. Users with high visibility are often selected as seeds to spread information and affect their adoption in target groups. The central theme of this paper is to answer how gender differences and similarities can impact the information spreading process. To this end, we first conduct a multi-faceted analysis showing that females do not reach top visibility (often referred to as the glass ceiling effect) via contrasting perspectives on an Instagram dataset: visibility vs. endorsement and network degree vs. interaction intensity, which are mainly discussed independently by the prior art. The analysis is based on two datasets: a large-scale Instagram data and a small-scale Facebook data. We explore various centrality measures, focusing on single hop interactions, i.e., intensity, degree, to multi-hop interactions, i.e., Pagerank, HI-index, and embedding index based on graph neural networks. Our analysis unveils that males and females interact differently depending on the interaction types, e.g., likes or comments on Instagram. Inspired by the observations of gender disparity, we propose a novel seeding framework, namely Disparity seeding, which aims to maximize information spread while reaching a target user group, e.g., a certain percentage of females -- promoting the influence of under-represented groups. An extensive simulation comparison with target-agnostic algorithms shows that the proposed Disparity can disseminate information according to the disparity requirement while effectively maximizing the information spread.