Urban Computing and Smart Cities Applications for the Knowledge Society

The papers in this urban computing special issue cover a framework and components of crowdsourcing, and a range of issues related to volunteered geographic information, including user behavior, brand popularity, recommendation system, and social analytics in social networks. Moreover, the special issue is devoted to capture different patterns and dynamics that characterize the big cities in order to reflect understanding of these phenomena and improving the quality of cities. The contributions in this special issue address the generation of urban data, their representation and analysis, and finally their relevance for urban planning and design, as well as the sustainability of smart cities. This volume is composed of 5 papers, which are intended to describe important challenges related to problems presented in big cities. For instance, in Saldaña et al., a methodology to obtain information related to traffic events such as accidents or congestions, from Twitter messages and RSS services is proposed. This work applies a text mining process on the posted messages to acquire the relevant data, then data are classified by using a machine learning technique. Later, the events are geocoded and transformed into geometric points to be represented on a map. The final repository lets data to be available for further works related to the traffic events on the study area. At the same time, in Escamilla et al., an approach for geocoding that takes advantage of the spatial relationships contained in the text of tweets, using semantic and spatial analyses is presented. The goal of this work is to associate spatial relationships, that were found in text with a spatial footprint, in order to determine the location of the event described in the tweet. This contribution is oriented towards improving the human ability to understand approximate references to locations, disambiguated by means of context and reasoning about spatial relationships. This approach is an important key to describe spatial environments and share volunteered geographic information. In Juaréz et al., a general framework for generating and sensing volunteered geographic information related to environmental noise is proposed. In this approach citizens play important roles, as users and map producers. Authors propose a mobile application in order to sense noise. Later, they used support vector machine as a machine learning approach for characterizing the phenomenon and analyzing with an acoustic noise prediction model the spatio-temporal sensed data. The information visualization is presented by means of heat maps that reflect the concentration and distribution of the acoustic noise information in a webmapping application. On the other hand, recommender systems with crowdsensing approaches are very and timely useful in this years. Thus, in Guzmán et al., an approach focused on locating and recommending health care centers within a certain range of distance is presented. This approach includes several Special Issue on Urban Computing and Smart Cities Applications for the Knowledge Society