Spatio-temporal sentiment hotspot detection using geotagged photos

A deep learning-based classifier is developed that predicts the emotion conveyed by an image that allows us to associate sentiment with place and performs spatial hotspot detection and shows that different emotions have distinct spatial distributions that match expectations.

Abstract

We perform spatio-temporal analysis of public sentiment using geotagged photo collections. We develop a deep learning-based classifier that predicts the emotion conveyed by an image. This allows us to associate sentiment with place. We perform spatial hotspot detection and show that different emotions have distinct spatial distributions that match expectations. We also perform temporal analysis using the capture time of the photos. Our spatio-temporal hotspot detection correctly identifies emerging concentrations of specific emotions and year-by-year analyses of select locations show there are strong temporal correlations between the predicted emotions and known events.