Untangling Topic Threads in Chat-Based Communication: A Case Study

Analyzing chat traffic has important applications for both the military and the civilian world. This paper presents a case study of a real-world application of chat analysis in support of team training exercise in the military. It compares the results of an unsupervised learning approach with those of a supervised classification approach. The paper also discusses some of the specific challenges presented by this domain. Analyzing microtexts for topic identification has many applications such as gauging the current topics that are capturing our collective attention, or discovering what people are saying about products, for example. While most of the focus of microtext analysis has been in the service of business intelligence, it has pretty powerful applications in the educational domain. Topic identification can be used t