Mobile devices and Internet-based applications are producing a significant volume of data that may be used to, at least partially, replace some of the hardware necessary to sense traffic systems. However, there are several issues related to such an agenda: data are heterogeneous, unstructured, may appear in natural language, are normally not geolocated, and there are balancing issues related to the use of such data. This means that all these issues must be treated via software, especially using machine learning techniques. In this paper, a methodology is proposed, which is based on: extraction and processing of relevant information from social media; determination of its context; explanation of transportation related phenomena in terms of their contexts; and prediction of traffic conditions. The methodology was applied to a case study using data from the city of Porto Alegre, Brazil. Results shown that it was possible to associate traffic-related and context data to predict the traffic conditions that were originally reported in a Twitter account.
Identifying traffic conditions from non-traffic related sources
Journal of Intelligent Transportation Systems ; 26 , 1 ; 116-127
2020-11-16
12 pages
Article (Journal)
Electronic Resource
Unknown
Identifying crash propensity using specific traffic speed conditions
Elsevier | 2004
|Identifying Intersection-Related Traffic Crashes for Accurate Safety Representation
Online Contents | 2009
|Traffic Stream Modeling under Heterogeneous Traffic Conditions
British Library Conference Proceedings | 2010
|