FEBRUARY 4, 2022
About the Presentation: In this talk, I will describe my lab’s research on the applications of natural language processing for automatic detection and identification of symptoms using data from the wild. Specifically, I describe our work on early identification of symptoms associated with novel pandemics using news reports and our work on detection of symptoms of mental disorders of users on social media.
About the Presenter: Soroush Vosoughi is an assistant professor of computer science at Dartmouth where he leads the minds, machines and society group. Part of the machine learning lab at Dartmouth, the group’s interests lie at the intersection of machine learning, natural language processing, network science, and social media analytics. Vosoughi’s lab develops and applies methods to mine and model unstructured data from various domains. The problems the lab investigates are varied and cross-disciplinary but mainly involve real-world problems and scenarios. Specifically, the lab is interested in developing computational models of complex social and linguistic behavior.
Prof. Vosoughi was awarded an Amazon Research Award in 2019. He is a member of the Institute for Security, Technology, and Society (ISTS) and the Quantitative Biomedical Sciences (QBS) program at Dartmouth. Prior to coming to Dartmouth, he was a postdoctoral associate at MIT and a fellow and later an affiliate at the Berkman Klein Center at Harvard University. As a postdoc at MIT, he was the technical director of the “Electome” project where his team of graduate and undergraduate students developed a collection of tools for automatic detection and categorization of election-related content on Twitter. The team was invited to be an official partner of the Commission on Presidential Debates during the 2016 elections. Prof. Vosoughi also served as a technical advisor to the nonprofit organization Cortico from 2016 to 2019. He received his PhD, MSc and BSc from MIT in 2015, 2010, and 2008 respectively.