BlueTempNet: A Temporal Multi-network Dataset of Social Interactions in Bluesky Social

Citation Author(s):
Ujun
Jeong
Arizona State University
Bohan
Jiang
Arizona State University
Zhen
Tan
Arizona State University
H. Russell
Bernard
Arizona State University
Huan
Liu
Arizona State University
Submitted by:
Ujun Jeong
Last updated:
Tue, 10/01/2024 - 23:40
DOI:
10.21227/yrsy-ee91
Data Format:
Network Graph
License:
Creative Commons Attribution
999 Views
Categories:
Artificial Intelligence
Machine Learning
Social Sciences
Communications
Keywords:
social networks, Bluesky Social, Decentralized Social Media, Temporal Graph Mining, Multi-network Analysis, User Behavior Modeling, Blocking and Group Sanction, Community Analysis
0
0 ratings - Please login to submit your rating.
ACCESS DATASET CITE SHARE/EMBED

Abstract 

Decentralized social media platforms like Bluesky Social (Bluesky) have made it possible to publicly disclose some user behaviors with millisecond-level precision. Embracing Bluesky's principles of open-source and open-data, we present the first collection of the temporal dynamics of user-driven social interactions. BlueTempNet integrates multiple types of networks into a single multi-network, including user-to-user interactions (following and blocking users) and user-to-community interactions (creating and joining communities). Communities are user-formed groups in custom Feeds, where users subscribe to posts aligned with their interests. Following Bluesky's public data policy, we collect existing Bluesky Feeds, including the users who liked and generated these Feeds, and provide tools to gather users' social interactions within a date range. This data-collection strategy captures past user behaviors and supports the future data collection of user behavior.

Instructions: 

Our networks are saved in GEXF as follows:

• graph_dimension1.gexf: Feed member interaction network saved in DiGraph object, where an edge has attributes sign and time and a node is Feed member.

• graph_dimension2.gexf: Feed creator interaction network saved in DiGraph object, where an edge has attributes sign and time, and a node is Feed creator.

• graph_dimension3.gexf: Community interaction network saved in a Graph object. Each node has a node attribute that can be a member, creator, or feed. Each edge has an edge attribute, either join or create, along with a time attribute.

• multi_graph.gexf: This is a MultiGraph object that integrates the three network dimensions. To facilitate ease of use, all undirected edges in the multigraph have been converted to bidirectional edges.

Metadata is saved in CSV as follows:

• user_metadata.csv

  1. Node Index (consistent across all GEXF files)
  2. Anonymized ID (decoded after ID request review)
  3. Number of Followers
  4. Number of Following
  5. Number of Posts

• feed_metadata.csv

  1. Node Index (consistent across all GEXF files)
  2. Feed URI (a unique identifier for profiles specific to the Bluesky Feed)
  3. Display Name of Feed
  4. Description of Feed
  5. Creator of Feed (given as Anonymized ID)
  6. Number of Likes on Feed

 

 

Scripts are used for collecting data from Bluesky Social.

Funding Agency: 
ONR
Grant Number: 
N00014-21-1-4002

Dataset Files

LOGIN TO ACCESS DATASET FILES

 

QUESTIONS?