Developing Smart Cities Services through Semantic Analysis of Social Streams

This paper presents a domain-agnostic framework for intelligent processing of textual streams coming from social networks. The framework implements a pipeline of techniques for semantic representation, sentiment analysis, automatic content classification, and provides an analytics console to get some findings from the extracted data. The effectiveness of the platform has already been proved by deploying it in two smart cities-related scenarios: in the first it was exploited to monitor the recovering state of the social capital of L'Aquila's city after the dreadful earthquake of April 2009, while in the latter a semantic analysis of the content posted on social networks was performed to build a map of the most at-risk areas of the Italian territory.