Activity space estimation with longitudinal observations of social media data

Lee, Jae Hyun; Davis, Adam Wilkinson; Yoon, Seo Youn; Goulias, Konstadinos G.

doi:10.1007/s11116-016-9719-1

Cited by 68 publications

(37 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The standard deviational ellipse of a set of GPS‐recorded points is defined as the area that covers approximately 68% of GPS points and that is centered on the average of the point pattern . Convex hulls are defined as polygons that contain all GPS points or tracks and have no angles greater than 180° . Studies have also utilized a nonparametric method known as 2D kernel density estimation in which a symmetrical kernel function is superimposed over a cluster of GPS points centered around its mean .…”

Section: Evolving Measures Of Be Exposurementioning

confidence: 99%

Obesity and the Built Environment: A Reappraisal

Drewnowski

Buszkiewicz

Aggarwal

et al. 2019

Obesity

View full text Add to dashboard Cite

The built environment (BE) has been viewed as an important determinant of health. Numerous studies have linked BE exposure, captured using a variety of methods, to diet quality and to area prevalence of obesity, diabetes, and cardiovascular disease. First‐generation studies defined the neighborhood BE as the area around the home. Second‐generation studies turned from home‐centric to person‐centric BE measures, capturing an individual’s movements in space and time. Those studies made effective uses of global positioning system tracking devices and mobile phones, sometimes coupled with accelerometers and remote sensors. Activity space metrics explored travel paths, modes, and destinations to assess BE exposure that was both person and context specific. However, as measures of the contextual exposome have become ever more fine‐grained and increasingly complex, connections to long‐term chronic diseases with complex etiologies, such as obesity, are in danger of being lost. Furthermore, few studies on obesity and the BE have included intermediate energy balance behaviors, such as diet and physical activity, or explored the potential roles of social interactions or psychosocial pathways. Emerging survey‐based applications that identify habitual destinations and associated travel patterns may become the third generation of tools to capture health‐relevant BE exposures in the long term.

show abstract

Section: Evolving Measures Of Be Exposurementioning

confidence: 99%

Obesity and the Built Environment: A Reappraisal

Drewnowski

Buszkiewicz

Aggarwal

et al. 2019

Obesity

View full text Add to dashboard Cite

show abstract

“…Although this is certainly an imperfect measure of the number of people at a location during particular time periods, we explore here whether it nonetheless provides some analytical purchase to understanding crime patterns. There is a growing body of research that utilizes social media to capture the presence of people throughout diverse locations of the city (Frias-Martinez and Frias-Martinez 2014; Lee, Davis, and Goulias 2016;Malleson and Birkin 2014). For example, a number of recent studies have used geolocated information from tweets, along with information on the home location of persons, to create alternative measures of "neighborhoods" that are based on the actual activity patterns of residents, rather than any other type of boundaries (Anselin and Williams 2015;Cranshaw, Schwartz, Hong, and Sadeh 2012;Shelton, Poorthuis, and Zook 2015).…”

Section: Does It Help Explain Local Crime Rates?mentioning

confidence: 99%

Using Social Media to Measure Temporal Ambient Population: Does it Help Explain Local Crime Rates?

Hipp¹,

Bates

Lichman

et al. 2018

Justice Quarterly

View full text Add to dashboard Cite

A challenge for studies assessing routine activities theory is accounting for the spatial and temporal confluence of offenders and targets given that people move about during the daytime and nighttime. We propose exploiting social media (Twitter) data to construct estimates of the population at various locations at different times of day, and assess whether these estimates help predict the amount of crime during two-hour time periods over the course of the day. We address these questions using crime data for 97,428 blocks in the Southern California region, along with geocoded information on tweets in the region over an eight month period. The results show that this measure of the temporal ambient population helps explain the level of crime in blocks during particular time periods. The use of social media data appear promising for testing various implications of routine activities and crime patterning theories, given their explicit spatial and temporal nature.

show abstract

“…Various studies [79][80][81][82] also examined social media data to understand the mobility behavior of a large group of people. Testing the possibility of evaluating the origin-destination matrix based on location-based social data was researched [83] or in another similar studies [84,85] where Twitter data was used to estimate OD matrices. The comparison between this new OD with the traditional values produced by the 4-step model proved the great potential of using social media data in modeling aggregate travel behavior.…”

Section: Social Media Datamentioning

confidence: 99%

Recent Progress in Activity-Based Travel Demand Modeling: Rising Data and Applicability

Tajaddini¹,

Rose²,

Kockelman³

et al. 2021

Models and Technologies for Smart, Sustainable and Safe Transportation Systems

View full text Add to dashboard Cite

Over 30 years have passed since activity-based travel demand models (ABMs) emerged to overcome the limitations of the preceding models which have dominated the field for over 50 years. Activity-based models are valuable tools for transportation planning and analysis, detailing the tour and mode-restricted nature of the household and individual travel choices. Nevertheless, no single approach has emerged as a dominant method, and research continues to improve ABM features to make them more accurate, robust, and practical. This paper describes the state of art and practice, including the ongoing ABM research covering both demand and supply considerations. Despite the substantial developments, ABM's abilities in reflecting behavioral realism are still limited. Possible solutions to address this issue include increasing the inaccuracy of the primary data, improved integrity of ABMs across days of the week, and tackling the uncertainty via integrating demand and supply. Opportunities exist to test, the feasibility of spatial transferability of ABMs to new geographical contexts along with expanding the applicability of ABMs in transportation policy-making.

show abstract

Activity space estimation with longitudinal observations of social media data

Cited by 68 publications

References 46 publications

Obesity and the Built Environment: A Reappraisal

Obesity and the Built Environment: A Reappraisal

Using Social Media to Measure Temporal Ambient Population: Does it Help Explain Local Crime Rates?

Recent Progress in Activity-Based Travel Demand Modeling: Rising Data and Applicability

Contact Info

Product

Resources

About