media-disinfo-simulation

You can simulate disinformation campaigns by loading a campaigns.json dataset into a Python environment and running a graph-based script to model network propagation. This requires the json and networkx libraries to generate an influence network and basic statistics.

Information operations modeling uses a network analysis framework to simulate disinformation campaigns. It applies predefined seed narratives to synthetic datasets, allowing computational social science researchers to safely study propagation dynamics and test mitigation strategies.

You test disinformation detection strategies by applying predefined anchor narratives to a synthetic dataset within NetworkX. This controlled sandbox allows you to evaluate mitigation effectiveness and study network propagation without causing real-world harm.

Yes, the simulation framework is designed for computational social science research scenarios including election interference, public health messaging, and social polarization analysis. You load relevant campaign datasets to model and study these specific information operations.

Yes, you need a campaigns.json file containing your dataset to run the network propagation simulations. This file is loaded directly into the workflow to generate the influence network and calculate basic propagation statistics.

A controlled sandbox provides a safe, reproducible environment to study information operations tradecraft without enabling real-world harm. It allows researchers to test detection and mitigation strategies on synthetic datasets before applying them to live environments.