Social Network modeling and applications

The use of social networks to understand societal issues has been widely studied across multiple disciplines, but scientists often struggle to access the data due to proprietary ownership and privacy concerns. This tutorial focuses on recent advances in network modeling, using synthetic networks to study real-world problems such as algorithmic bias, and ranking inequalities, and includes a review of different types of generative models and how to perform a network selection analysis.

Download .ical

Target audience

This tutorial is targeted to researchers attending The Web Conference (in-person) who want to learn more about (i) random network generator models, (ii) deployment of synthetic networks with and without attributes and specific edge formation mechanisms, (iii) model selection given an empirical network, and (iv) how to exploit synthetic networks for sharing data with privacy guarantees, and to understand real-world issues including algorithmic bias, and ranking inequalities.

Participants must have a basic knowledge of coding in Python.

Pre-requisites

All our exercises can be run on Google Colab (you only need a Google account). However, if you prefer to run the exercises in your laptop, please follow the instructions from our GitHub repository. Additionally, make sure the latest versions of the packages netin and graph-tool are running and follow this quick start guide.