PhaseVis1: What, when, where, and who in visualizing the four phases of emergency management through the lens of social media

The Four Phase Model of Emergency Management has been widely used in developing emergency/disaster response plans. However, the model has received criticism contrasting the clear phase distinctions in the model with the complex and overlapping nature of phases indicated by empirical evidence. To investigate how phases actually occur, we designed PhaseVis based on visualization principles, and applied it to Hurricane Isaac tweet data. We trained three classification algorithms using the four phases as categories. The 10-fold cross-validation showed that Multi-class SVM performed the best in Precision (0.8) and Naïve Bayes Multinomial performed the best in F-1 score (0.782). The tweet volume in each category was visualized as a ThemeRiverTM, which shows the ‘What’ aspect. Other aspects 'When', 'Where', and 'Who' are also integrated. The classification evaluation and a sample use case indicate that PhaseVis has potential utility in disasters, aiding those investigating a large disaster tweet dataset.