TY - JOUR
T1 - Classification of traffic related short texts to analyse road problems in urban areas
AU - Saldana-Perez, Ana María Magdalena
AU - Moreno-Ibarra, Marco
AU - Tores-Ruiz, Miguel
N1 - Publisher Copyright:
© Authors 2017. CC BY 4.0 License.
PY - 2017/9/25
Y1 - 2017/9/25
N2 - 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.
AB - 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.
KW - Classification
KW - Data Analysis
KW - Human sensors
KW - Machine Learning
KW - Traffic
KW - Volunteered Geographic Information
UR - http://www.scopus.com/inward/record.url?scp=85032626265&partnerID=8YFLogxK
U2 - 10.5194/isprs-archives-XLII-4-W3-91-2017
DO - 10.5194/isprs-archives-XLII-4-W3-91-2017
M3 - Artículo de la conferencia
AN - SCOPUS:85032626265
SN - 1682-1750
VL - 42
SP - 91
EP - 97
JO - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
JF - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences - ISPRS Archives
IS - 4W3
T2 - 2nd International Conference on Smart Data and Smart Cities, UDMS 2017
Y2 - 4 October 2017 through 6 October 2017
ER -