Mitigating Bias in Big Data for Transportation

Griffin, Graeme; Mulhall, Megan; Simek, Chris; Riggs, William

doi:10.1007/s42421-020-00013-0

Cited by 27 publications

(12 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biases in MDD-derived transportation metrics can be reduced or mitigated by combining measured trip patterns with ancillary data sources, including roadway counts, census data, and surveys, as well as by applying local knowledge and planning judgment in evaluating the resulting data products ( 12 ). The effects of differential sampling rates across demographic or user groups may affect the accuracy of O-D data but would not be anticipated to affect congestion and travel time metrics, as traffic conditions encountered by smartphone owners in the same place and time would not be expected to vary between visitors of different demographic groups.…”

Section: Literature Reviewmentioning

confidence: 99%

Mobile Device Data for Parks and Public Lands Transportation Planning: A Framework for Evaluation and Applications

Baird¹,

Stinger²,

Cole

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Examination of mobile device data in transportation research and planning practices has occurred in a variety of contexts. However, little investigation of its potential to enhance transportation planning processes in parks and public lands has happened to date. The National Park Service partnered with the U.S. Department of Transportation Volpe Center and Colorado Department of Transportation to investigate how mobile device data can enhance regional and park-level transportation planning efforts by better answering questions about transportation system usage patterns. Using the StreetLight Insight data platform, we evaluated desired use cases and communication strategies for scoping, evaluating, procuring, and applying mobile device data to park- and system-level planning challenges. The analyses of a Colorado statewide visitor data sample were found to be promising data sources for planning tasks including understanding the relationships between gateway communities and parks, internal traffic/visitor flows, dwell times at internal park destinations, and speeds on park- and park-adjacent roadways.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Mobile Device Data for Parks and Public Lands Transportation Planning: A Framework for Evaluation and Applications

Baird¹,

Stinger²,

Cole

et al. 2022

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Previous research has indicated the biases of emerging data, which in turn threaten the outcome legitimacy of these data. In particular, Strava is associated with several biases: (i) demographic bias towards young and white males [74]; (ii) social desirability bias, where the recorded trips may over-reflect trips with a sense of achievement and overlook mundane journeys [13]; and (iii) self-selection bias that arises when the participants can include or exclude themselves from the sample [129]. BSSs provide data on all their users, eliminating the potential of social desirability and self-selection biases.…”

Section: Biasesmentioning

confidence: 99%

“…The advent and ubiquity of information and communication technology, including smartphones and wearable devices, has allowed for emerging AT data (hereinafter emerging data) ventures. These datasets are considered Big Data, characterized by the three v's: volume (very large), variety (highly complex) and velocity (high growth rate), making them unmanageable through traditional methods [13]. Such unprecedented data also, however, provide new opportunities and challenges to aid the transport paradigm shift toward AT.…”

Section: Introductionmentioning

confidence: 99%

Sources and Applications of Emerging Active Travel Data: A Review of the Literature

2021

View full text Add to dashboard Cite

Active travel (AT) has the potential to integrate with, or in some cases substitute for, trips taken by motorized transportation. In this paper we review relevant research on AT outcomes to address the potential of AT and emerging data sources in supporting the transport paradigm shift toward AT. Our analysis identifies physical, mental, built and physical environmental, monetary, and societal outcomes. Traditional methods used to acquire AT data can be divided into manual methods that require substantial user input and automated methods that can be employed for a lengthier period and are more resilient to inclement weather. Due to the proliferation of information and communication technology, emerging data sources are prevailing and can be grouped into social fitness networks, in-house developed apps, participatory mapping, imagery, bike sharing systems, social media, and other types. We assess the emerging data sources in terms of their applications and potential limitations. Furthermore, we identify developing policies and interventions, the potential of imagery, focusing on non-cycling modes and addressing data biases. Finally, we discuss the challenges of data ownership within emerging AT data and the corresponding directions for future work.

show abstract

“…For example, there are legitimate concerns about bias of the Strava sample, which is disproportionally used by middle-aged, white men (Garber, Watkins, & Kramer, 2019), that have led to development of many studies of how best to use Strava (Mcnair & Arnold, 2016). As with many big data analyses, it is critical that when using Strava data for research and practice applications that expert opinion, local knowledge, and appropriate goals and metrics are also considered (Griffin, Mulhall, Simek, & Riggs, 2020). Additionally, methods to correct the bias in Strava data have been developed (Roy et al, 2019) to map all ridership.…”

Section: Gps/ Accelerometrymentioning

confidence: 99%

Crowdsourced data for bicycling research and practice

et al. 2020

View full text Add to dashboard Cite

Cities are promoting bicycling for transportation as an antidote to increased traffic congestion, obesity and related health issues, and air pollution. However, both research and practice have been stalled by lack of data on bicycling volumes, safety, infrastructure, and public attitudes. New technologies such as GPS-enabled smartphones, crowdsourcing tools, and social media are changing the potential sources for bicycling data. However, many of the developments are coming from data science and it can be difficult evaluate the strengths and limitations of crowdsourced data. In this narrative review we provide an overview and critique of crowdsourced data that are being used to fill gaps and advance bicycling behaviour and safety knowledge. We assess crowdsourced data used to map ridership (fitness, bike share, and GPS/accelerometer data), assess safety (web-map tools), map infrastructure (OpenStreetMap), and track attitudes (social media). For each category of data, we discuss the challenges and opportunities they offer for researchers and practitioners. Fitness app data can be used to model spatial variation in bicycling ridership volumes, and GPS/accelerometer data offer new potential to characterise route choice and origin-destination of bicycling trips; however, working with these data requires a high level of training in data science. New sources of safety and near miss data can be used to address underreporting and increase predictive capacity but require grassroots promotion and are often best used when combined with official reports. Crowdsourced bicycling infrastructure data can be timely and facilitate comparisons across multiple cities; however, such data must be assessed for consistency in route type labels. Using social media, it is possible to track reactions to bicycle policy and infrastructure changes, yet linking attitudes expressed on social media platforms with broader populations is a challenge. New data present opportunities for improving our understanding of bicycling and supporting decision making towards transportation options that are healthy and safe for all. However, there are challenges, such as who has data access and how data crowdsourced tools are funded, protection of individual privacy, representativeness of data and impact of biased data on equity in ARTICLE HISTORY

show abstract

Mitigating Bias in Big Data for Transportation

Cited by 27 publications

References 64 publications

Mobile Device Data for Parks and Public Lands Transportation Planning: A Framework for Evaluation and Applications

Mobile Device Data for Parks and Public Lands Transportation Planning: A Framework for Evaluation and Applications

Sources and Applications of Emerging Active Travel Data: A Review of the Literature

Crowdsourced data for bicycling research and practice

Contact Info

Product

Resources

About