Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W3, 91-97, 2017
https://doi.org/10.5194/isprs-archives-XLII-4-W3-91-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 4.0 License.
 
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 Instituto Politécnico Nacional, Centro de Investigación en Computación (CIC), Mexico City, México. Av. Juan de Dios Bátiz, Esq. Miguel Othón de Mendizábal. Colonia Nueva Industrial Vallejo. Delegación Gustavo A. Madero. C.P.07738. México
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.
Conference paper (PDF, 1523 KB)


Citation: Saldana-Perez, A. M. M., Moreno-Ibarra, M., and Tores-Ruiz, M.: CLASSIFICATION OF TRAFFIC RELATED SHORT TEXTS TO ANALYSE ROAD PROBLEMS IN URBAN AREAS, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-4/W3, 91-97, https://doi.org/10.5194/isprs-archives-XLII-4-W3-91-2017, 2017.

BibTeX EndNote Reference Manager XML