Collaborative Research: SaTC: TTP: Medium: iDRAMA.cloud: A Platform for Measuring and Understanding Information Manipulation

Suny At Binghamton, Binghamton NY

Investigators

Abstract

Social media has become crucial to our society, especially when it comes to the rapid and broad dissemination of information. However, bad actors have exploited social media, for example via information manipulation. While there have been efforts made to address the problem, there are a variety of challenges that make it difficult to study and combat information manipulation in practice. This project aims to address these challenges by transitioning a set of algorithms, software frameworks, and system designs out of the research lab into the hands of active practitioners to help identify and mitigate information manipulation (misinformation and dis-information). This project’s novelties are the design and development of production capable, open-source software suite to enable the rapid collection, management, and analysis of social media data. The project’s broader significance and importance is primarily related to ensuring the stability of the information ecosystem. The production ready software created under the project can also help educate future practitioners about fundamental software development skills in the areas of systems, machine learning, and data science. In this proposal, the project team aims to transition the tooling that has enabled cutting edge research into practice. The project team will develop a full featured crawler construction toolkit built from experiences working on a variety of large-scale social media data collection systems. Next, the project team will develop a data characterization and augmentation toolkit, integrating state-of-the-art techniques from information manipulation research. Finally, the project team will develop a set of data access and sharing APIs, including a federation subsystem, that practitioners can build new technologies around. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.