Traditional urban planning processes typically happen in offices and behind desks. Modern types of civic participation can enhance those processes by acquiring citizens' ideas and feedback in participatory sensing approaches like "People as Sensors". As such, citizen-centric planning can be achieved by analysing Volunteered Geographic Information (VGI) data such as Twitter tweets and posts from other social media channels. These user-generated data comprise several information dimensions, such as spatial and temporal information, and textual content. However, in previous research, these dimensions were generally examined separately in single-disciplinary approaches, which does not allow for holistic conclusions in urban planning. This paper introduces TwEmLab, an interdisciplinary approach towards extracting citizens' emotions in different locations within a city. More concretely, we analyse tweets in three dimensions (space, time, and linguistics), based on similarities between each pair of tweets as defined by a specific set of functional relationships in each dimension. We use a graph-based semi-supervised learning algorithm to classify the data into discrete emotions (happiness, sadness, fear, anger/disgust, none). Our proposed solution allows tweets to be classified into emotion classes in a multi-parametric approach. Additionally, we created a manually annotated gold standard that can be used to evaluate TwEmLab's performance. Our experimental results show that we are able to identify tweets carrying emotions and that our approach bears extensive potential to reveal new insights into citizens' perceptions of the city.
Even though much research has been conducted on the safety of cycling infrastructures, most previous approaches only make use of traditional and proven methods based upon datasets such as accident statistics, road infrastructure data, or questionnaires. Apart from typical surveys, which are known to face numerous limitations from a psychological and sociological viewpoints, the question of how perceived safety can best be assessed is still widely unexplored. Thus, this paper presents an approach for bio-physiological sensing to identify places in urban environments which are perceived as unsafe by cyclists. Specifically, a number of physiological parameters like ECG, skin conductance, skin temperature and heart rate variability are analysed to identify moments of stress. Together with data gathered through a People as Sensors app, these stress levels can be mapped to specific emotions. This method was tested in a pilot study in Cambridge, MA (USA), which is presented in this paper. Our findings show that our method can identify places with emotional peaks, particularly fear and anger. Although our results can be qualitatively interpreted and used in urban planning, more research is necessary to quantitatively and automatically generate recommendations from the measurements for urban planners.
This chapter introduces the 'Urban Emotions' approach. It focuses on integrating humans' emotional responses to the urban environment into planning processes. The approach is interdisciplinary and anthropocentric, i.e. citizens and citizens' perceptions are highlighted in this concept. To detect these emotions/perceptions, it combines methods from spatial planning, geoinformatics and computer linguistics to give a better understanding of how people perceive and respond to static and dynamic urban contexts in both time and geographical space. For collecting and analyzing data on the emotional perception to urban space, we use technical and human sensors as well as georeferenced social media posts, and extract contextual emotion information from them. The resulting novel information layer provides an additional, citizen-centric perspective for urban planners. In addition to technical and methodological aspects, data privacy issues and the potential of wearables are discussed in this chapter. Two case studies demonstrate the transferability of the approach into planning processes. This approach will potentially reveal new insights for the perception of geographical spaces in spatial planning.
In contrast to previous approaches, Urban Emotions defines Smart Cities not only as technology-enriched cities, but also emphasises the human factor -Smart Citizens. This is due to the fact that the question of how people perceive a city and how they feel about it has always been important in urban planning and management. In this paper we present our approach for crowdsourcing physiological conditions and subjective emotions by combining data from technical sensors (measuring psycho-physiological parameters) and human sensors ("People as Sensors" contributing subjectively perceived emotions). Furthermore, we couple this crowdsourcing approach with a technical architecture to harmonise and integrate the sensor data via standardised service interfaces (Sensor Web Enablement -SWE) to allow for generic access for further analysis and visualisation. Finally, we discuss the use of emotion information in urban planning and point out related privacy issues together with a number of strategies to mitigate those.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.