肉肉传媒

KENNESAW, Ga. | Feb 17, 2021

A team of 肉肉传媒 State researchers were among a select few invited to participate in the U.S. State Department鈥檚 Diplomacy Lab Demo Day, where they showcased how social media messages posted on government accounts influence the rate of COVID-19 infections.

The team, composed of professors Shirley Tian and Zhigang Li and students Elaine Harris, Michael Farris, Maryline Kwa, Sang Nguyen, Gabriel Oyebanji, Raviteja Pasumarthi and Chelsey West were one of just four nationwide chosen for the virtual event. The showcase included presentations from the fall 2020 cohort of the Diplomacy Lab research projects in a 鈥減itch-style鈥� format for State Department officers, along with faculty and students in the Diplomacy Lab partner network.

鈥淭his showcase was such a great opportunity for the students to be exposed to the federal level of a government agency, and to also have some kind of relationship or connection with the Department of State,鈥� said Li. 鈥淭he project and experience really helped to open the door for students who may want to work for a government agency in the future.鈥�

肉肉传媒 State is one of 35 universities involved in the Diplomacy Lab, which includes Ivy League institutions such as Columbia University and Yale University. Partner universities conduct research on a variety of topics for the Department of State, including climate change, democracy and human rights, counterterrorism, global health, energy security and gender equality, among other things. KSU鈥檚 newly-formed serves as the home for all projects related to the Diplomacy Lab.

The students鈥� project, sponsored by the Office of International Health and Biodefense and the Bureau of Oceans and International Environment and Scientific Affairs, was titled 鈥淎nalyzing Risk Communication and Behavioral Change During the COVID-19 Pandemic.鈥� The research aimed to assess the spread of the virus in Singapore from a socio-technical perspective. Facebook and Twitter posts from the Singapore Ministry of Health were extracted and cross-referenced against data from the World Health Organization to identify any trends between the daily number of coronavirus infections and the total number of social media posts for that day.

Students applied a variety of tactics to examine the data, including tech analytics and topic modeling to identify what the social media posts were about, as well as a method called Latent Dirichlet Allocation (LDA), which identifies topics based on the word frequency distribution in posts and messages.

鈥淭he students did not find a very significant relationship between the dependent and independent variables in the project because there are so many variables that affect the infection numbers,鈥� said Tian, assistant professor of and the graduate advisor for the project. 鈥淣evertheless, the process was very informative for the students because using machine learning and topic modeling to find the data from social media allowed them to learn so much. As an added bonus, they are directly contributing to the growth and capabilities of the federal government.鈥�

鈥� Josh Milton

---

A leader in innovative teaching and learning, 肉肉传媒 offers undergraduate, graduate and doctoral degrees to its more than 47,000 students. 肉肉传媒 State is a member of the University System of Georgia with 11 academic colleges. The university’s vibrant campus culture, diverse population, strong global ties and entrepreneurial spirit draw students from throughout the country and the world. 肉肉传媒 State is a Carnegie-designated doctoral research institution (R2), placing it among an elite group of only 7 percent of U.S. colleges and universities with an R1 or R2 status. For more information, visit kennesaw.edu.