Analyzing Social Media Data Having Discontinuous Underlying Dynamics

2013 INFORMS Annual Meeting Minneapolis
Analytics Section Sponsored Session
Presented by Les Servi, The MITRE Corporation
In this presentation, Servi discusses his development of a real time algorithm which identifies times of emotional discontinuity as reflected in social media. The talk formulates the optimization problem to solve, develops an algorithm to solve it using dynamic programming, and illustrates the new method by analyzing mood shifts reflected in 380,000 Twitter messages related to one of the most popular soccer teams, Manchester United, during their 2011-12 season.