Topic Models from Crash Narrative Reports of Motorcycle Crash Causation Study

Transportation Research Record: Journal of the Transportation R

Sarkar

2022

Self Cite

The COVID-19 pandemic has affected the lives of everyone from almost every perspective. Research communities from many domains have contributed to quantifying and mitigating the influence of the ongoing pandemic. The public depend on news media for reliable information. At the start of the pandemic in March 2020, many news media articles started to report on quieter roads resulting from travel restriction and work from home mandates, but also more excessive speeding and more traffic fatalities. Although the news media’s representation of the crash-speed association is often not based on data-driven safety analysis, the extent to which the media place emphasis on such news content has never been adequately quantified. The current study performed content analysis and text mining (both text network analysis and topic modeling) to explore the representations of speed-crash association in news media (local, national, and international) to provide insights into the generated news content. Findings reveal that topics such as a surge in fatal crashes, careless driving, driving under the influence, law enforcement, and equity issues, as well as impacts on pedestrians and bicyclists, were frequently highlighted by local, national, and international news media during the pandemic era.

Section: Methodsmentioning

confidence: 99%

News Media Mining to Explore Speed-Crash-Traffic Association During COVID-19

Transportation Research Record: Journal of the Transportation R

Sarkar

2022

Self Cite

“…DOT FHWA’s MCCS. Das et al ( 22 ) investigated the matched case-control study of the MCCS containing a very wide list of crash-contributing factors associated with motorcycle crash occurrences.…”

Section: Literature Reviewmentioning

confidence: 99%

Bayesian Network for Motorcycle Crash Severity Analysis

Transportation Research Record: Journal of the Transportation R

Vierkant²,

González³

et al. 2023

Self Cite

Given the lack of protective structural barriers and advanced restraints, motorcyclists are vulnerable road users. In 2020 in the United States, motorcycle-involved fatalities occurred 28 times more frequently per vehicle mile traveled than passenger car occupant fatalities, causing 5,579 motorcycle-related fatalities—the highest number of motorcyclists killed since 1975. By identifying patterns and relationships between key contributing factors, strategies for reducing motorcycle crashes can be developed. In addition to current efforts, additional research must be conducted using innovative avenues, with increased funding. Bayesian networks can better discover the relationships between potential speed compliance variables. This study used six years (2014 to 2019) of motorcycle crash data in Louisiana to determine the conditional probabilities of the influential factors. In addition to the high contribution of alcohol involvement, two-way undivided roadways, 35 to 44 year-old drivers involved in improper driving behaviors, and crash types are the underlying factors associated with a considerable increase in motorcycle crash severity. The findings of this study can also be used for decision making and strategy development for motorcycle safety.

“…Text mining and topic modeling have become topics of interest among transportation engineers. In recent years, many studies applied these techniques to identify hidden insights from unstructured textual contents (21)(22)(23)(24)(25)(26)(27)(28)(29).…”

Section: Literature Reviewmentioning

confidence: 99%

Twelve-Year Analysis of Transportation Research Board Annual Meeting’s Official Hashtag

Transportation Research Record: Journal of the Transportation R

Dutta

2021

Self Cite

Twitter, among other social media platforms, has become more popular over time. Social media platforms underpin the way scholars share ideas, propagate the latest emergence of evidence, and adopt new practices, by providing a virtual platform for interacting, socializing, and sharing information from academic conferences with the outside world beyond the physical location. The Transportation Research Board Annual Meeting (TRBAM) is the largest annual conference for transportation engineering and science, and the hashtag for the conference, #TRBAM, was used first in 2009. This paper aims to perform an observational study based on the interactions on Twitter surrounding this hashtag by collecting all original #TRBAM tweets for 12 years (2009–2020). A general trend in the data is that the quantitative measures (tweets, retweets, and favorites) are all much higher during the conference month compared with other months. Top trending topics included: transit, safety, bike or non-motorized mode of transportation, data, and freight. Overall, the communication pattern shows more dispersion than the central tendency. The findings of this study highlight the need to implement and improve strategies to help transportation research communities encourage continuous and active participation during and after conferences. More active engagement among attendees will help maintain the momentum of information sharing and expand the traffic safety platform globally.