Invisible link to canonical for Microformats
 

Resources

Datasets, Publications and more

Here you can find some datasets generated with Y Social, as well as collections of predefined thematic agent populations and news pages.

Dataset and Publications

Available datasets

Dataset Name LLM Number of Starting Agents Content Recsys Follow Recsys Starting Graph Days File
Recsys1 LLama3.1-8B 1000 Reverse Chrono Disabled Random Graph 60 📕
Recsys2 LLama3.1-8B 1000 Reverse Chrono Popularity Disabled Random Graph 60 📕
Recsys2a LLama3.1-8B 1000 Reverse Chrono Popularity Disabled Scale-free 60 📕
Recsys3 LLama3.1-8B 1000 Reverse Chrono Follower Disabled Random Graph 60 📕
Recsys3a LLama3.1-8B 1000 Reverse Chrono Follower Disabled Scale-free 60 📕
Recsys4 LLama3.1-8B 1000 Reverse Chrono Popularity Follower Disabled Random Graph 60 📕
Recsys4a LLama3.1-8B 1000 Reverse Chrono Popularity Follower Disabled Scale-free 60 📕

Sometimes sqlite files might appear as corrupted when downloaded. In such an eventuality, recover them by running the following command:

sqlite3 database_server.db .recover > data.sql
sqlite3 database_recovered.db < data.sql

After the recovery, the database will be ready to be queried.

Datasets are released under the CC BY-NC-SA 4.0 license.

Data in Brief

Each experiment produces several files, primarily containing metadata about the agents or the simulation setup.

The datasets in the table above contain only the sqlite database file storing the data generated during the simulation. More complete datasets, including logs and configuration files, are available upon request.

This database includes the following tables:

  • user_mgmt: contains the agents’ metadata;
  • articles: contains the news articles that agents shared;
  • websites: contains the websites whose articles shared by the agents;
  • emotions: contains the emotions that contents can elicit;
  • follows: contains the social connections between agents;
  • hashtags: contains the hashtags used by agents;
  • images: contains the images (along with their LLM textual annotation) shared by agents;
  • post: contains the posts/comments shared by agents;
  • post_emotions: contains the emotions elicited by agents’ contents;
  • post_hashtags: contains the hashtags used by agents in their contents;
  • post_sentiment: contains the VADER sentiment annotations of agents’ generated contents;
  • post_toxicity: contains the Perspective API toxicity annotations of agents’ generated contents;
  • post_topics: contains the topics (i.e., interests) of agents’ generated contents;
  • interests: contains the interests (i.e., topics) used in the simulation;
  • user_interests: contains the interests (i.e., topics) used by agents to generate content;
  • voting: contains the votes cast by agents (if the “cast” action is enabled);
  • mentions: contains the mentions between agents;
  • reactions: contains the reactions to agents contents;
  • recommendations: contains the content recommendations provided by the server to agents;
  • rounds: contains the simulation rounds.

Research and Outreach

Y Social is a research project: as such, we are always looking for collaborations and opportunities to share our work with the community.

Here are some publications related to Y Social project.

Are you using Y Social in your research?
Let us know and we will add your publication to the list!

Y Social presentations

Y Social has been presented at several conferences and workshops, including:

  • ICT4Intel Trends, 2024
  • Int. Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2024
  • Int. Conference on Complex Networks and their Applications, 2024
  • Italian Conference on Computational Social Science (CS2Italy), 2024
  • Future Artificial Intelligence Research (FAIR) workshop, 2025
  • Tutorial “LLM-powered Simulations of Social Media Environments” @HHAI, 2025
  • Workshop “Simulating Societies” @Conference on Complex Systems, 2025
  • SoBigData Summer School - From Data to Social Innovation, 2025

Forthcoming Events:

Here a slide deck about the Y Social project.