Uncovering built environment influences on the integration of bike-sharing and metro

Insights from topic modeling


METADATA ONLY

Date

2022-05-20

Publication Type

Other Conference Item

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Bike-sharing is emerging as a convenient transfer mode for metros. While increasing attention paid on the use of bike-sharing, few attempts have been made to understand how built environment attributes affect the synergy of metro with bicycles. This study aims to examine the refined relationship between the integrated usage and built environment within the catchment areas of the metro stations. Inspired by the idea in text mining, this study proposes a topic-based data mining algorithm to unravel bike-sharing usage patterns and land use functions at station level. Specifically, the term frequency-inverse document frequency (TF-IDF) method is adopted to extract key built environment; then the Latent Dirichlet Allocation (LDA) is employed to identify underlying land use functions with their probabilities. Meanwhile, based on the daily tendency of the integrated travel, the latent bike-sharing usage patterns are also estimated using LDA. At last, multivariate regression model is applied to explore the correlation between station-level land use functions and bike-sharing usage patterns, and scrutinize the built environment effects on the integrated usage. This study is helpful in developing a bike- friendly built environment that facilitates the seamless connection between bike-sharing and the metro.

Publication status

published

External links

Editor

Book title

Journal / series

Volume

Pages / Article No.

Publisher

STRC

Event

22nd Swiss Transport Research Conference (STRC 2022)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Bike-sharing; Metro station; Built environment; Topic modeling; Data mining

Organisational unit

03521 - Axhausen, Kay W. (emeritus) / Axhausen, Kay W. (emeritus) check_circle
02655 - Netzwerk Stadt u. Landschaft ARCH u BAUG / Network City and Landscape ARCH and BAUG

Notes

Conference lecture held on May 20, 2022.

Funding

Related publications and datasets