Wednesday, April 8th    3:00 PM

Abstract:

The importance of quantifying the nature and intensity of emotional states at the level of populations is evident: we would like to know how individuals feel, so that we may improve public policy, build more successful organizations, and more fully understand economic and social phenomena. By incorporating direct human assessment of words, we measure and analyze the psychological valence (or pleasantness) of a diverse set of texts which reflect human experience. We discuss several striking observations regarding the relationship between author demographics (e.g. age, location) and the emotional impact of millions of weblogs. This project is in collaboration with Peter Sheridan Dodds at UVM.

Bio: Dr. Danforth earned a B.S. with honors in Mathematics and Physics from Bates College in 2001. In 2006, he received a Ph.D. in Applied Mathematics and Scientific Computation from the University of Maryland, College Park. He is currently on the faculty of the College of Engineering and Mathematical Sciences at the University of Vermont, where his work is on modeling and predictability of a variety of biological, social, and physical systems. Descriptions of his work are available at his website: http://www.uvm.edu/~cdanfort/