Spatio-Temporal Sentiment Hotspot Detection Using Geotagged Photos
This work provides a method for spatio-temporal sentiment analysis from visual data, which is incremental as it applies existing techniques to geotagged photos for hotspot detection.
The paper tackled the problem of analyzing public sentiment over space and time by using geotagged photos, developing a deep learning classifier to predict image emotions, and found that emotions have distinct spatial distributions and strong temporal correlations with known events.
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.