The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-4/W3
https://doi.org/10.5194/isprs-archives-XLII-4-W3-91-2017
https://doi.org/10.5194/isprs-archives-XLII-4-W3-91-2017
25 Sep 2017
 | 25 Sep 2017

CLASSIFICATION OF TRAFFIC RELATED SHORT TEXTS TO ANALYSE ROAD PROBLEMS IN URBAN AREAS

A. M. M. Saldana-Perez, M. Moreno-Ibarra, and M. Tores-Ruiz

Keywords: Volunteered Geographic Information, Human sensors, Machine Learning, Classification, Data Analysis, Traffic

Abstract. The Volunteer Geographic Information (VGI) can be used to understand the urban dynamics. In the classification of traffic related short texts to analyze road problems in urban areas, a VGI data analysis is done over a social media’s publications, in order to classify traffic events at big cities that modify the movement of vehicles and people through the roads, such as car accidents, traffic and closures. The classification of traffic events described in short texts is done by applying a supervised machine learning algorithm. In the approach users are considered as sensors which describe their surroundings and provide their geographic position at the social network. The posts are treated by a text mining process and classified into five groups. Finally, the classified events are grouped in a data corpus and geo-visualized in the study area, to detect the places with more vehicular problems.