- Joseph Sventek
In this talk, we mainly present two projects related to improve information trustworthiness/cybersecurity by using data science. In the first project, we present the problem of detecting coordinated free text campaigns in large-scale social media. Specifically, we propose and evaluate a content-driven framework for effectively linking free text posts with common “talking points” and extracting campaigns from large-scale social media. In the second project, we present a framework for “pulling back the curtain” on crowdturfers to reveal their underlying ecosystem. Concretely, we analyze the types of malicious tasks and the properties of requesters and workers in crowdsourcing sites, and link these tasks (and their associated workers) on crowdsourcing sites to social media. We develop statistical user models to automatically differentiate these workers and regular social media users.
Kyumin Lee is an expert on data science and mining, cybersecurity and social computing over large-scale networked information systems like the Web, social media and crowd-based systems. On one hand, he has conducted research on threats to these systems, designed and developed methods to detect social spammers, collective attention spam, and campaigns, to analyze crowdsourcing platforms and to build community-based trust. On the other hand, he has mined and analyzed large-scale location-sharing services, learning management system data, and crowd-based services. His research works have been featured hundreds times by media such as the MIT Technology Review and the Wired. His research work received nomination for Best Paper Award at the 19th ACM International Conference on Intelligent User Interfaces, 2014. He is a recipient of NSF CAREER award and Google Faculty Research award. He received the CS Faculty Service award in 2016.