It is interesting to exploit the user-generated content (UGC) and to use it with a view to infer new data; volunteered geographic information (VGI) is a concept derived from UGC, whose main importance lies in its continuously updated data. The present approach tries to explode the use of VGI by collecting data from a social network and a RSS service; the short texts collected from the social network are written in Spanish language; text mining and a recovery information processes are applied over the data in order to remove special characters on text and to extract relevant information about the traffic events on the study area; then data are geocoded. The texts are classified by using a machine learning algorithm into five classes, each of them represents a specific traffic event or situation.
TopBackground
User generated content (UGC) is any publication on internet, done by users of web services such as blogs, wikis, forums, social networks, podcast and chats. It is used in many applications, including: researches, information and news spread, problems processing, disaster management, and collaborative mapping. UGC has originated some other concepts, volunteered geographic information (VGI) and crowdsourcing are two of them (Chard, 2015).
Crowdsourcing is the process of getting ideas, information, or work done, from a group of interested people; it has been a recurrent data and services source for some businesses and researches (Chard, 2015). Mobile devices as smartphones, mobile GPS, cartographic applications and social networks, make crowdsourcing possible.
According to Wen Lin (2013), VGI is composed of volunteered information generated by users, who have not a geographic specialized knowledge, but are interested on provide data with geographic characteristics; such data are employed on many web services as Open Street Map (OSM), WikiMapia, Google Maps, among others. This association between VGI and web services are the GeoWeb basis.