A Persuasive Approach to Combating Misinformation

Safwan Hossain, Andjela Mladenovic, Yiling Chen, Gauthier Gidel
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:18926-18943, 2024.

Abstract

Bayesian Persuasion is proposed as a tool for social media platforms to combat the spread of misinformation. Since platforms can use machine learning to predict the popularity and misinformation features of to-be-shared posts, and users are largely motivated to share popular content, platforms can strategically signal this informational advantage to change user beliefs and persuade them not to share misinformation. We characterize the optimal signaling scheme with imperfect predictions as a linear program and give sufficient and necessary conditions on the classifier to ensure optimal platform utility is non-decreasing and continuous. Next, this interaction is considered under a performative model, wherein platform intervention affects the user’s future behaviour. The convergence and stability of optimal signaling under this performative process are fully characterized. Lastly, we experimentally validate that our approach significantly reduces misinformation in both the single round and performative setting.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-hossain24b, title = {A Persuasive Approach to Combating Misinformation}, author = {Hossain, Safwan and Mladenovic, Andjela and Chen, Yiling and Gidel, Gauthier}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {18926--18943}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/hossain24b/hossain24b.pdf}, url = {https://proceedings.mlr.press/v235/hossain24b.html}, abstract = {Bayesian Persuasion is proposed as a tool for social media platforms to combat the spread of misinformation. Since platforms can use machine learning to predict the popularity and misinformation features of to-be-shared posts, and users are largely motivated to share popular content, platforms can strategically signal this informational advantage to change user beliefs and persuade them not to share misinformation. We characterize the optimal signaling scheme with imperfect predictions as a linear program and give sufficient and necessary conditions on the classifier to ensure optimal platform utility is non-decreasing and continuous. Next, this interaction is considered under a performative model, wherein platform intervention affects the user’s future behaviour. The convergence and stability of optimal signaling under this performative process are fully characterized. Lastly, we experimentally validate that our approach significantly reduces misinformation in both the single round and performative setting.} }
Endnote
%0 Conference Paper %T A Persuasive Approach to Combating Misinformation %A Safwan Hossain %A Andjela Mladenovic %A Yiling Chen %A Gauthier Gidel %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-hossain24b %I PMLR %P 18926--18943 %U https://proceedings.mlr.press/v235/hossain24b.html %V 235 %X Bayesian Persuasion is proposed as a tool for social media platforms to combat the spread of misinformation. Since platforms can use machine learning to predict the popularity and misinformation features of to-be-shared posts, and users are largely motivated to share popular content, platforms can strategically signal this informational advantage to change user beliefs and persuade them not to share misinformation. We characterize the optimal signaling scheme with imperfect predictions as a linear program and give sufficient and necessary conditions on the classifier to ensure optimal platform utility is non-decreasing and continuous. Next, this interaction is considered under a performative model, wherein platform intervention affects the user’s future behaviour. The convergence and stability of optimal signaling under this performative process are fully characterized. Lastly, we experimentally validate that our approach significantly reduces misinformation in both the single round and performative setting.
APA
Hossain, S., Mladenovic, A., Chen, Y. & Gidel, G.. (2024). A Persuasive Approach to Combating Misinformation. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:18926-18943 Available from https://proceedings.mlr.press/v235/hossain24b.html.

Related Material