Hi everyone!

This week at the Applied Statistics Workshop we will be welcoming Dean Knox and Christopher Lucas, PhD Candidates in Political Science at MIT and Government at Harvard, respectively.  They will be presenting work entitled A Model for Measuring Emotion in Political Speech with Audio Data.  Please find the abstract below and on the website.

As usual, we will meet in CGIS Knafel Room 354 from noon to 1:30pm, and lunch will be provided.  See you all there! To view previous Applied Statistics presentations, please visit the website.

-- Aaron Kaufman

Title: A Model for Measuring Emotion in Political Speech with Audio Data

Abstract: Though we generally assume otherwise, humans communicate using more than bags of words alone. Auditory and visual cues convey important information, such as emotion, in many phenomena of interest to political scientists. However, in part due to the relative difficulty of processing audio data, research has disproportionately focused on the textual component of pre-transcribed corpora. We develop a new hidden Markov model for emotional analysis to complement and extend existing methods for text analysis. The tools and model are applied to oral arguments in the Supreme Court and Presidential campaign speeches.

-- 
Aaron R Kaufman
PhD Candidate, Harvard University
Department of Government
818.263.5583