Open Geospatial Data Contribution Towards Sentiment Analysis Within the Human Dimension of Smart Cities

Abstract

In recent years, there is a widespread growth of smart cities. These cities aim to increase the quality of life for its citizens, making living in an urban space more attractive, livelier, and greener. In order to accomplish these goals, physical sensors are deployed throughout the city to oversee numerous features such as envi- ronmental parameters, traffic, and the resource consumption. However, this concept lacks the human dimension within an urban context, not reflecting how humans perceive their environment and the city’s services. In this context there is a need to consider sentiment analysis within a smart city as a key element toward coherent decision making, since it is important not only to assess what people are doing, but also, why they are behaving in a certain way. In this sense, this work aims to assemble tools and methods that can collect, analyze and share information, based on User Generated spatial Content and Open Source Geospatial Science. The emotional states of citizens were sensed through social media data sources (Twitter), by extracting features (location, user profile information and tweet content by using the Twitter Streaming API) and applying machine learning techniques, such as natural language processing (Tweepy 3.0, Python library), text analysis and computational linguis- tics (Textblob, Python library). With this approach we are capable to map abstract concepts like sentiment while linking both quantitative and qualitative analysis in human geography. This work would lead to understand and evaluate the “immaterial” and emotional dimension of the city and its spatial expression, where location-based social networks, can be established as pivotal geospatial data sources revealing the pulse of the city.