A deep learning approach for detecting traffic accidents from social media data. (January 2018)

• Record Type: Journal Article
• Authors: Zhang, Zhenhua; He, Qing; Gao, Jing; Ni, Ming
• Is Part Of: Transportation research. Volume 86(2018)
• Page Start: 580
• Page End: 596
• Publication Date: 2018-01
• Subjects: Traffic accident detection -- Tweet -- Social media -- Association rules -- Deep learning; Transportation -- Periodicals; Transportation -- Technological innovations -- Periodicals; 388.011
• DOI: 10.1016/j.trc.2017.11.027
• Languages: English
• ISSNs: 0968-090X

Abstract

Highlights: Use deep learning to detect traffic accidents with social media. Examine 1-year 3 million tweet data from both Northern Virginia and NYC. Validated by official traffic accident records and 15, 000 loop detectors. 66% of the labeled tweets can be located by the accident log. More than 80% of them can be tied to nearby abnormal traffic data. Abstract: This paper employs deep learning in detecting the traffic accident from social media data. First, we thoroughly investigate the 1-year over 3 million tweet contents in two metropolitan areas: Northern Virginia and New York City. Our results show that paired tokens can capture the association rules inherent in the accident-related tweets and further increase the accuracy of the traffic accident detection. Second, two deep learning methods: Deep Belief Network (DBN) and Long Short-Term Memory (LSTM) are investigated and implemented on the extracted token. Results show that DBN can obtain an overall accuracy of 85% with about 44 individual token features and 17 paired token features. The classification results from DBN outperform those of Support Vector Machines (SVMs) and supervised Latent Dirichlet allocation (sLDA). Finally, to validate this study, we compare the accident-related tweets with both the traffic accident log on freeways and traffic data on local roads from 15, 000 loop detectors. It is found that nearly 66% of the accident-related tweets can be located by the accident log and more than 80% of them can be tied to nearby abnormal traffic data. Several important issues of using Twitter to detect traffic accidents have been brought up by the comparison including the location and time bias, as well as the characteristics of influential users and hashtags.