Increasingly, social media has been used as a platform for providing timely crisis communication during a disaster. Unfortunately, rumor spreading, and in particular, rumors that are later proven to be untrue, have been identified as critical issues for the use of social media during disasters. For example, messages that mistakenly describe a particular hospital or evacuation route as closed have circulated during recent events. This project will contribute to the NSF's Big Idea "Harnessing Data for 21st Century Science and Engineering" by conducting fundamental research in data science and engineering in the field of social media and disaster management. In particular, this project will build novel models of how rumors currently spread on social media during disasters to improve rumor control and debunking during future disasters. This scientific research contribution thus supports NSF's mission to promote the progress of science and to advance our national welfare. In this case, the benefits will be insights to improve crisis information distribution and rumor management practices, which will save lives, economic losses, and reduce panic, anger and confusion during disasters. This project will support multiple PhD dissertations and MS theses, and involve undergraduate students from under-represented backgrounds.
The research objective of this project is to model and optimize the decision-making processes of misinformed social media users during disasters, to study effective rumor detection strategies, and to design and analyze rumor spreading and debunking models for social media users during disasters. To achieve the research objectives, the researchers will use social network analysis, content analysis, decision analysis, game theory, optimization, and simulation, to: (1) collect and analyze social media data to identify potential rumor responding behaviors during disasters and the impact of their responses on rumor spreading; (2) detect rumors from other information by developing a rumor detection algorithm based on rumor text, comments, and spreading patterns; (3) design and validate a decision making model of individual social media users; and (4) study a new rumor spreading model to study the interaction of spreading and debunking processes of social media information.
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.
