MEWS: Real-time Social Media Manipulation Detection and Analysis

Trenton Ford, Michael Yankoski, William Theisen, Tom Henry, Farah Khashman, Katherine Dearstyne, Tim Weninger, Pamela Bilo Thomas
Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, PMLR 176:325-329, 2022.

Abstract

This article presents a beta-version of MEWS (Misinformation Early Warning System). It describes the various aspects of the ingestion, manipulation detection, and graphing algorithms employed to determine–in near real-time–the relationships between social media images as they emerge and spread on social media platforms. By combining these various technologies into a single processing pipeline, MEWS can identify manipulated media items as they arise and identify when these particular items begin trending on individual social media platforms or even across multiple platforms. The emergence of a novel manipulation followed by rapid diffusion of the manipulated content suggests a disinformation campaign.

Cite this Paper


BibTeX
@InProceedings{pmlr-v176-ford22a, title = {MEWS: Real-time Social Media Manipulation Detection and Analysis}, author = {Ford, Trenton and Yankoski, Michael and Theisen, William and Henry, Tom and Khashman, Farah and Dearstyne, Katherine and Weninger, Tim and Bilo Thomas, Pamela}, booktitle = {Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track}, pages = {325--329}, year = {2022}, editor = {Kiela, Douwe and Ciccone, Marco and Caputo, Barbara}, volume = {176}, series = {Proceedings of Machine Learning Research}, month = {06--14 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v176/ford22a/ford22a.pdf}, url = {https://proceedings.mlr.press/v176/ford22a.html}, abstract = {This article presents a beta-version of MEWS (Misinformation Early Warning System). It describes the various aspects of the ingestion, manipulation detection, and graphing algorithms employed to determine–in near real-time–the relationships between social media images as they emerge and spread on social media platforms. By combining these various technologies into a single processing pipeline, MEWS can identify manipulated media items as they arise and identify when these particular items begin trending on individual social media platforms or even across multiple platforms. The emergence of a novel manipulation followed by rapid diffusion of the manipulated content suggests a disinformation campaign.} }
Endnote
%0 Conference Paper %T MEWS: Real-time Social Media Manipulation Detection and Analysis %A Trenton Ford %A Michael Yankoski %A William Theisen %A Tom Henry %A Farah Khashman %A Katherine Dearstyne %A Tim Weninger %A Pamela Bilo Thomas %B Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track %C Proceedings of Machine Learning Research %D 2022 %E Douwe Kiela %E Marco Ciccone %E Barbara Caputo %F pmlr-v176-ford22a %I PMLR %P 325--329 %U https://proceedings.mlr.press/v176/ford22a.html %V 176 %X This article presents a beta-version of MEWS (Misinformation Early Warning System). It describes the various aspects of the ingestion, manipulation detection, and graphing algorithms employed to determine–in near real-time–the relationships between social media images as they emerge and spread on social media platforms. By combining these various technologies into a single processing pipeline, MEWS can identify manipulated media items as they arise and identify when these particular items begin trending on individual social media platforms or even across multiple platforms. The emergence of a novel manipulation followed by rapid diffusion of the manipulated content suggests a disinformation campaign.
APA
Ford, T., Yankoski, M., Theisen, W., Henry, T., Khashman, F., Dearstyne, K., Weninger, T. & Bilo Thomas, P.. (2022). MEWS: Real-time Social Media Manipulation Detection and Analysis. Proceedings of the NeurIPS 2021 Competitions and Demonstrations Track, in Proceedings of Machine Learning Research 176:325-329 Available from https://proceedings.mlr.press/v176/ford22a.html.

Related Material