Gemsec

2 datasets tagged as the tag “Gemsec”.

2 datasets.

GEMSEC Facebook Page-Page Networks (Cumulative) Analyzed

A Facebook (social media platform) dataset of 134,833 Facebook pages and 1,379,403 undirected mutual-like edges across 8 page categories (company, politician, tvshow, government, artist, new_sites, public_figure, athletes), collected by Rozemberczki et al. via Facebook Graph API, distributed via GEMSEC/SNAP. Each record contains undirected edges between Facebook pages representing mutual likes; pages categorized as company, politician, TV show, government, artist, news site, public figure, or athlete; node IDs namespaced by category. The dataset is notable for its multi-category Facebook page network with known ground-truth category labels per node, enabling direct evaluation of community detection and node classification algorithms across heterogeneous page types. Intended for research into community detection, node classification, graph embedding, cross-category network comparison, and social media page recommendation research.

134.8K records134.8K nodes1.4M edges2019

GEMSEC HR: Deezer Romania Friendship Network Analyzed

A Deezer (Romania) dataset of 54,573 users, 498,202 friendships, collected by Rozemberczki et al. via Deezer music streaming service (November 2017). Each record contains undirected edges between Deezer users representing mutual friendships, with node attributes including genre preferences (84 distinct genres). Friendship network from Deezer music streaming service in Romania, with rich genre preference metadata enabling music-based community detection and user behavior analysis. Suitable for community detection, graph embedding, music preference analysis, social network analysis, recommendation systems.

54.6K records54.6K nodes498.2K edges2019