Vehicular traffic analysis from social media data

Shekhar, Himanshu; Setty, Shankar; Mudenagudi, Uma

doi:10.1109/icacci.2016.7732281

Cited by 21 publications

(14 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [23], the authors built an artificial neural network (ANN) that classifies traffic congestion conditions based on data sourced from Twitter and Waze. The authors of [24] explored applying data mining methods to predict traffic congestion and movement patterns from social media posts.…”

Section: Related Workmentioning

confidence: 99%

Empowering Real-Time Traffic Reporting Systems With NLP-Processed Social Media Data

Wan

Lucic

Ghazzai

et al. 2020

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

Current urbanization trends are leading to heightened demand of smarter technologies to facilitate a variety of applications in intelligent transportation systems. Automated crowdsensing constitutes a strong base for ITS applications by providing novel and rich data streams regarding congestion tracking and real-time navigation. Along with these wellleveraged data streams, drivers and passengers tend to report traffic information to social media platforms. Despite their abundance, the use of social media data in ITS has gained more and more attention as of now. In this paper, we develop an automated Natural Language Processing (NLP)-based framework to empower and complement traffic reporting solutions by text mining social media, extracting desired information, and generating alerts and warning for drivers. We employ the finetuned Bidirectional Encoder Representations from Transformers classification model to filer and classify data. Then, we apply the Question-Answering model to extract necessary information characterizing the reported incident such as its location, occurrence time, and nature of the incidents. Afterwards, we convert the collected information into alerts to be integrated into personal navigation assistants. Finally, we compare the recently posted incident reports from both official authorities and social media in order to provide more complete incident pictures and suggest some open research directions.

show abstract

Section: Related Workmentioning

confidence: 99%

Empowering Real-Time Traffic Reporting Systems With NLP-Processed Social Media Data

Wan

Lucic

Ghazzai

et al. 2020

IEEE Open J. Intell. Transp. Syst.

View full text Add to dashboard Cite

show abstract

“…They showed an accuracy of 92% in the road condition monitoring. Shekhar et al [110] focused on the vehicular traffic monitoring using more than one social media, instead of traditional traffic sensors and satellite information which can be quite expensive. Using a Natural Language Processing (NLP) technique, they examined Twitter and Facebook posts to address traffic problems at a specific location and time interval.…”

Section: B Extra-vehicular Sensormentioning

confidence: 99%

“…Septiana et al [109] proposed the categorization of the road conditions, based on text mining of Facebook feeds. In the same way, Shekhar et al [110] focused on the vehicular traffic monitoring using Facebook and Twitter posts. Pan et al [86] also used social media data to enrich the anomalies detection based on GPS from vehicles trajectories.…”

Section: Traffic Monitoring and Managementmentioning

confidence: 99%

“…Besides, projects that developed their own data acquisition infrastructure [41], [46], [48], [60], [61], [63], [90], [91], for instance, do not make all data available to the community for some reasons: (i) vehicular data has commercial value and may not be available at all; (ii) those initiatives keep their propriety to advance their investigations and innovations; and (iii) data privacy may become a problem in case of releasing the datasets. These are facts that help us to understand the small availability of vehicular data, which reflects in just a few investigations [51], [52], [85], [87], [108], [110], [112], [113] that use data provided by third parties.…”

Section: A Data Creationmentioning

confidence: 99%

“…The subjectivity of data present in social media, for instance, calls for strategies that allow its understanding. Using a Natural Language Processing (NLP) approach [108] and its algorithms like Term Frequency-Inverse Document Frequency (TF-IDF) [112], Spell correction and Stop-word filter [111], Latent Dirichlet Allocation (LDA) [113], and regular [110] expression, it is possible to reduce the noise and subjectivity of texts written by users. Fuzzy logic may also be used to remove the subjective aspect of these datasets.…”

Section: Data Preparationmentioning

confidence: 99%

See 2 more Smart Citations

Vehicular Data Space: The Data Point of View

Rettore

Maia

Villas

et al. 2019

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Over the years, governments and automakers launched initiatives to improve road traffic efficiency, safety, and people mobility. They have been working on various aspects of intelligent transportation systems (ITSs), which aim to improve decision-making, availability of information, and communication technologies to provide applications and services to boost the transportation systems. The development of new applications and services for ITS depends on the availability of different data sources, what it is not the current case. Many studies focus on the communication issues of applications and their associated challenges. To reveal the recent vehicular data use, we examined the most remarkable studies of the last few years, which describe services and applications for ITS, however with a focus on the data employed by them. We introduce the concept of vehicular data space (VDS), which is then used to describe the vehicular scenario from the perspective of data. Moreover, we outline a taxonomy, according to the different data sources. We also categorize the applications, highlighting the data each one used in their approach. Finally, we present some challenges and open issues related to the process for data creation, data preparation, data processing, and data use. In a nutshell, this paper constitutes one of the first holistic surveys on services and applications for ITSs, focusing on the data used by them, as well as their future challenges. Index Terms-Vehicular data space (VDS), vehicular sensor data, connected vehicles, intelligent transportation system (ITS), heterogeneous data, vehicular ad-hoc network (VANET). I. INTRODUCTIONM ORE and more cities will have to deal with significant issues related to transportation and traffic because people and goods are in constant need for quicker and safer mobility modes. The number of fatalities and injuries on the road has achieved an alarming scenario. Globally, 1.3 million people die every year, and up to 50 million suffer severe injuries. These facts have a direct impact on the economics of nations, leading to costs in the order of about 2% to 5% of the Gross Domestic Product (GDP) in many countries [1]. It is also reported that traffic congestion results in critical economic and environmental costs. In 2011, 498 U.S. urban areas were

show abstract