Describing and Classifying Post-Mortem Content on Social Media

Abstract

As the quantity of user profiles on social media grows, so does the number of post-mortem profiles. In this paper, we present a computational linguistic analysis of post-mortem social media profiles. Specifically, we provide an analysis of pre- vs. post-mortem language use, followed by a description of classifiers we developed that can accurately classify the mortality of social media profiles. These results shed initial lights into the ways in which people speak to the dead, and mark a first step toward accurately identifying mortality on a large scale.