Trip distribution modeling with Twitter data

Pourebrahim, Nastaran; Sultana, Selima; Niakanlahiji, Amirreza; Thill, Jean‐Claude

doi:10.1016/j.compenvurbsys.2019.101354

Cited by 40 publications

(12 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results showed that the similarity among flows was quite high for Manhattan but less remarkable for the other boroughs. At the same level, [29] proposed the integration of TWT data with census tracts and LEHD Origin-Destination Employment Statistics (LODES) for New York city to estimate its commuting trip distribution. The results showed that the aggregation of TWT data to the model created from the more traditional data along with the use of the Random Forest technique yielded the best performance for developing dynamic models of trip distribution.…”

Section: Related Workmentioning

confidence: 99%

“…The resulting set of tweets was used to extract the TWT-based OD matrix. To do so, we used a well-known trip-extraction procedure from tweets [10,29]. In particular, a trip is regarded as sequence of two consecutive tweets tw u ma o → tw u ma d from a user u posted at different MAs ma o , ma d (ma o = ma d ) whose time difference is less than t , tw u ma d .timestamp − tw u ma o .timestamp ≤ t ( t > 0).…”

Section: Twitter Mobility Datasetmentioning

confidence: 99%

“…Unlike the aforementioned datasources, OSN-location data can be easily retrieved from Application Programming Interfaces (APIs). These data have been used in several types of mobility-related analyses at different spatial scales and scenarios [8,23,29,34].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An analysis of twitter as a relevant human mobility proxy

et al. 2022

View full text Add to dashboard Cite

During the last years, the analysis of spatio-temporal data extracted from Online Social Networks (OSNs) has become a prominent course of action within the human-mobility mining discipline. Due to the noisy and sparse nature of these data, an important effort has been done on validating these platforms as suitable mobility proxies. However, such a validation has been usually based on the computation of certain features from the raw spatiotemporal trajectories extracted from OSN documents. Hence, there is a scarcity of validation studies that evaluate whether geo-tagged OSN data are able to measure the evolution of the mobility in a region at multiple spatial scales. For that reason, this work proposes a comprehensive comparison of a nation-scale Twitter (TWT) dataset and an official mobility survey from the Spanish National Institute of Statistics. The target time period covers a three-month interval during which Spain was heavily affected by the COVID-19 pandemic. Both feeds have been compared in this context by considering different mobility-related features and spatial scales. The results show that TWT could capture only a limited number features of the latent mobility behaviour of Spain during the study period.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Twitter Mobility Datasetmentioning

confidence: 99%

See 1 more Smart Citation

An analysis of twitter as a relevant human mobility proxy

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The results were compared with data from surveys and census of the transportation council, showing a notable similarity in some city boroughs. Similarly for the same city, Pourebrahim et al [26] combined Twitter data with census data and employment statistics to predict the commuting trip distribution in New York, obtaining a more accurate model than only using the static data. Another example of using Twitter for predicting mobility patterns, in this case for detecting road-traffic events, is shown by Alomari et al [27].…”

Section: Related Workmentioning

confidence: 99%

Human Mobility Prediction With Region-Based Flows and Water Consumption

et al. 2021

View full text Add to dashboard Cite

We are witnessing an increasing need to accurately measure people's mobility as it has become an instrumental factor for the development of innovative services in multiple domains. In this context, several ICT solutions have relied on location-based technologies such as GPS, WiFi or Bluetooth to track individuals movements. However, these technologies are limited by the privacy restrictions of data providers. In this paper we propose a methodology to robustly predict citizens' mobility patterns based on heterogeneous data from different sources. Particularly, our methodology focuses on a human mobility predictor based on a low-resolution mobility dataset and the use of water consumption data as a facilitator of this prediction task. As a result, this work explores whether the water consumption within a geographical region can reveal human activity patterns relevant from the point of view of the mobility mining discipline. This approach has been tested in a residential area near Madrid (Spain) obtaining quite promising results.

show abstract

“…Radiation models are limited by data capacity, using only population distribution and ignoring the growing availability of urban data [1]. Machine learning approaches have also been proposed for trip distribution modeling, including random forest [19,20,23]. These machine learning models make use of rich urban data and can better model complex nonlinearities.…”

Section: Related Work 21 Commuting Flow Predictionmentioning

confidence: 99%

Transportation Scenario Planning with Graph Neural Networks

Alice¹,

Pradhan²,

Liu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Providing efficient human mobility services and infrastructure is one of the major concerns of most mid-sized to large cities around the world. A proper understanding of the dynamics of commuting flows is, therefore, a requisite to better plan urban areas. In this context, an important task is to study hypothetical scenarios in which possible future changes are evaluated. For instance, how the increase in residential units or transportation modes in a neighborhood will change the commuting flows to or from that region? In this paper, we propose to leverage GMEL, a recently introduced graph neural network model, to evaluate changes in commuting flows taking into account different land use and infrastructure scenarios. We validate the usefulness of our methodology through real-world case studies set in two large cities in Brazil.

show abstract

Trip distribution modeling with Twitter data

Cited by 40 publications

References 45 publications

An analysis of twitter as a relevant human mobility proxy

An analysis of twitter as a relevant human mobility proxy

Human Mobility Prediction With Region-Based Flows and Water Consumption

Transportation Scenario Planning with Graph Neural Networks

Contact Info

Product

Resources

About