摘要: |
This research project will build an open-source socio-transportation analytic (STAT) toolbox for public transit system planning, in an effort to integrate social media and general transit feed specification (GTFS) data for transit agencies in evaluating and enhancing the performance of public transit system. This toolbox is novel and essential to transit agencies in two aspects. First, it enables the integration, analysis and visualization of two major new open transportation data: social media and GTFS data, to support transit decision making. Second, it allows transit agencies to evaluate service network efficiency and access equity of transit systems in a cohesive manner, and identify areas for improvement to better achieve these multi-dimensional objectives. The toolbox will employ a combination of data mining, geographical information systems, and transportation network modeling. The STAT will be an open-source toolbox and will be made publicly available. The project team will engage two transit agencies, the Utah Transit Authority (UTA) and TriMet, to evaluate the usability of the toolbox. It will assist agencies in evaluating the overall system performance and identifying existing public transit connectivity gap, particularly for disadvantaged populations in reaching essential services. It can also act as a decision support tool for recommending improvements (e.g., prioritize the stations and routes, identify the necessity for introducing a new line within existing infrastructure, etc.) The project ties to the National Institute for Transportation and Communities (NITC) theme of improving mobility of people and creating vibrant communities. The project team expects that it can be adapted over time to cover different geographies and incorporate new data sources. In addition to serving transit agency staff, the tool can be used in university curriculum and by advocacy organizations engaged in transportation decision-making. Finally, the project lays the foundation for NITC developing other open-source tools using big data. |