AI System Behavioral Analysis

This project focuses on understanding how AI systems exhibit emergent behaviors when deployed at scale, particularly examining recommendation algorithms and content moderation systems. We use innovative methodologies including counterfactual experiments to causally estimate AI system effects.

Using computational methods to study AI system behavior and understand their impact on user experiences and societal outcomes.

Key research areas include:

Emergent behavior analysis in large-scale AI deployments
Counterfactual evaluation of AI system interventions
Cross-platform comparative studies of AI system effects
Long-term impact assessment of AI-mediated interactions

Our work addresses fundamental questions about the balance between user agency and algorithmic influence in shaping online experiences. Through rigorous experimental design, we aim to separate correlation from causation in AI system evaluation.

References

2024

Causally estimating the effect of YouTube’s recommender system using counterfactual bots

Homa Hosseinmardi, Amir Ghasemian, Miguel Rivera-Lanas, Manoel Horta Ribeiro, Robert West, and Duncan J Watts

Proceedings of the National Academy of Sciences, 2024

Bib

@article{hosseinmardi2023causally,
  title = {Causally estimating the effect of YouTube’s recommender system using counterfactual bots},
  author = {Hosseinmardi, Homa and Ghasemian, Amir and Rivera-Lanas, Miguel and Horta Ribeiro, Manoel and West, Robert and Watts, Duncan J},
  journal = {Proceedings of the National Academy of Sciences},
  volume = {121},
  number = {8},
  pages = {e2313377121},
  year = {2024},
  publisher = {National Acad Sciences},
}

2023

Deplatforming did not decrease Parler users’ activity on fringe social media

Manoel Horta Ribeiro, Homa Hosseinmardi, Robert West, and Duncan J Watts

PNAS nexus, 2023

Bib

@article{horta2023deplatforming,
  title = {Deplatforming did not decrease Parler users’ activity on fringe social media},
  author = {Horta Ribeiro, Manoel and Hosseinmardi, Homa and West, Robert and Watts, Duncan J},
  journal = {PNAS nexus},
  volume = {2},
  number = {3},
  pages = {pgad035},
  year = {2023},
  publisher = {Oxford University Press US},
}

2021

Examining the consumption of radical content on YouTube

Homa Hosseinmardi, Amir Ghasemian, Aaron Clauset, Markus Mobius, David M Rothschild, and Duncan J Watts

Proceedings of the National Academy of Sciences, 2021

Bib

@article{hosseinmardi2021examining,
  title = {Examining the consumption of radical content on YouTube},
  author = {Hosseinmardi, Homa and Ghasemian, Amir and Clauset, Aaron and Mobius, Markus and Rothschild, David M and Watts, Duncan J},
  journal = {Proceedings of the National Academy of Sciences},
  volume = {118},
  number = {32},
  pages = {e2101967118},
  year = {2021},
  publisher = {National Acad Sciences},
}