Urban Emotions-Geo-Semantic Emotion Extraction from Technical Sensors, Human Sensors and Crowdsourced Data

How people in the city perceive their surroundings depends on a variety of dynamic and static context factors such as road traffic, the feeling of safety, urban architecture, etc. Such subjective and context-dependent perceptions can trigger different emotions, which enable additional insights into the spatial and temporal configuration of urban structures. This paper presents the Urban Emotions concept that proposes a human-centred approach for extracting contextual emotional information from human and technical sensors. The methodology proposed in this paper consists of four steps: (1) detecting emotions using wristband sensors, (2) "ground-truthing" these measurements using a People as Sensors location-based service, (3) extracting emotion information from crowdsourced data like Twitter, and (4) correlating the measured and extracted emotions. Finally, the emotion information is mapped and fed back into urban planning for decision support and for evaluating ongoing planning processes.