A Blue Start: A large-scale pairwise and higher-order social network dataset

2025-05-16

AI Summary

Existing network research predominantly focuses on pairwise interactions, overlooking critical higher-order group interactions prevalent in applications such as disease transmission and information diffusion. Moreover, empirical data—especially large-scale benchmark datasets jointly capturing both pairwise relations and higher-order group structures—remain scarce. Method: Leveraging the open Bluesky API, we systematically collect and structurally parse user-generated “starter packs”—self-organized higher-order groups—and their associated follower-followee relationships. Contribution/Results: We introduce the first large-scale social network dataset integrating both pairwise and higher-order structural information: it comprises 26.7 million nodes, 1.6 billion directed follow edges, and 301,000 higher-order groups. This dataset fills a critical gap in empirical higher-order network research and provides a foundational benchmark for modeling group-level dynamics.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Application Domains: Social Networks
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Computational social science
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Bridging structured and unstructured data

Abstract

Large-scale networks have been instrumental in shaping the way that we think about how individuals interact with one another, developing key insights in mathematical epidemiology, computational social science, and biology. However, many of the underlying social systems through which diseases spread, information disseminates, and individuals interact are inherently mediated through groups of arbitrary size, known as higher-order interactions. There is a gap between higher-order dynamics of group formation and fragmentation, contagion spread, and social influence and the data necessary to validate these higher-order mechanisms. Similarly, few datasets bridge the gap between these pairwise and higher-order network data. Because of its open API, the Bluesky social media platform provides a laboratory for observing social ties at scale. In addition to pairwise following relationships, unlike many other social networks, Bluesky features user-curated lists known as"starter packs"as a mechanism for social network growth. We introduce"A Blue Start", a large-scale network dataset comprising 26.7M users and their 1.6B pairwise following relationships and 301.3K groups representing starter packs. This dataset will be an essential resource for the study of higher-order network science.

Problem

• Lack of large-scale datasets for higher-order social interactions
• Gap between theoretical higher-order dynamics and empirical validation
• Need for datasets bridging pairwise and group-based network structures

Innovation

• Utilizes Bluesky's open API for data collection
• Includes pairwise and higher-order interaction data
• Features user-curated starter packs for network analysis