Journal
SENSORS
Volume 21, Issue 9, Pages -Publisher
MDPI
DOI: 10.3390/s21092964
Keywords
volunteered geographic information; crowdsourcing; spatiotemporal analysis; support vector regression; geographic information system; twitter
Funding
- Secretaria de Investigacion y Posgrado [20201863, 20210162]
- CONACyT [PN-2016/2110]
- Instituto Politecnico Nacional
Ask authors/readers for more resources
This paper introduces how to geocode and predict traffic congestion using social media data, build a prediction model, and display spatial distribution using heat maps, demonstrating that social media is a good alternative for gathering dynamic city information.
Smart cities are characterized by the use of massive information and digital communication technologies as well as sensor networks where the Internet and smart data are the core. This paper proposes a methodology to geocode traffic-related events that are collected from Twitter and how to use geocoded information to gather a training dataset, apply a Support Vector Machine method, and build a prediction model. This model produces spatiotemporal information regarding traffic congestions with a spatiotemporal analysis. Furthermore, a spatial distribution represented by heat maps is proposed to describe the traffic behavior of specific and sensed areas of Mexico City in a Web-GIS application. This work demonstrates that social media are a good alternative that can be leveraged to gather collaboratively Volunteered Geographic Information for sensing the dynamic of a city in which citizens act as sensors.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available