A new emotion–based hot and cold spots detection method to assess the citizen’s discomfort due to heatwaves in the northeastern area of the province of Naples (Italy)

A spatial analysis technique known as “hot and cold spots identification” is used in a variety of situations to identify areas where a particular phenomena is either highly or weakly concentrated or experienced. Numerous hot (cold) spot detection methods have been proposed in the literature. Clustering methods are typically used to extract hot and cold spots as polygons on maps; the more precisely the hot (cold) spot area is determined, the more computationally complex the clustering algorithm becomes. Furthermore, these methods do not take into account the hidden information provided by users through social networks, significant for detecting the presence of hot (cold) spots based on the emotional reactions of citizens. To overcome these critical points, we propose a GIS–based hot and cold spot detection framework encapsulating a classification model of emotion categories of documents extracted from social streams connected to the investigated phenomenon is implemented. The study area is split into subzones; residents’ postings during a predetermined time period is retrieved and analyzed for each subzone. With the aid of a fuzzy–based approach to classifying emotions, the proposed model measures the prevalence of pleasant and unpleasant emotional categories in each subzone at various time intervals. The subzones in which uneasy emotions predominate over the examined time period are referred to as hot (cold) spots. Since the exact geometric shape of the point is not necessary to be detected, the proposed framework has the advantage of greatly reducing the CPU time required by cluster–based hot and cold spot detection techniques. Our framework has been put to the test in the study region, which is made up of towns in the northeastern part of the province of Naples, to find hot and cold places related to the misery of residents due to heat waves. (Italia). The results show that the hot spots, where the greatest discomfort is felt, correspond to areas with a high population/building density, on the contrary, cold spots cover urban areas having a lower population density.