Datasets

Here some datasets generated by Y Social simulations. Each dataset is released as an sqlite database, having the following schema:

Database Schema

The main tables are:

• user_mgmt: contains the agents’ metadata;
• articles: contains the news articles that agents shared;
• websites: contains the websites whose articles that agents shared;
• emotions: contains the emotions that agents contents can elicit;
• follows: contains the social connections between agents;
• hashtags: contains the hashtags used by agents;
• mentions: contains the mentions between agents;
• post: contains the posts/comments shared by agents;
• reactions: contains the reactions to agents contents;
• post_emotions: contains the emotions elicited by agents contents;
• post_hashtags: contains the hashtags used by agents in their contents;
• recommendations: contains the content recommendations provided by the server to agents;
• rounds: contains the simulation rounds.

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

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

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

Available datasets

Datasets are released under the CC BY-NC-SA 4.0 license.
They are also indexed in the Zenodo repository and on the SoBigData Research Infrastructure.

Publications

Here some publications related to Y Social project.

• Rossetti, G. et al. Y Social: an LLM-powered Social Media Digital Twin, arXiv:2408.00818, 2024.

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