Data-enabled public preferences inform integration of autonomous vehicles with transit-oriented development in Atlanta. (March 2017)

• Record Type: Journal Article
• Authors: Lu, Zhongming; Du, Rundong; Dunham-Jones, Ellen; Park, Haesun; Crittenden, John
• Is Part Of: Cities. Volume 63(2017)
• Page Start: 118
• Page End: 127
• Publication Date: 2017-03
• Subjects: Autonomous vehicle -- Social preference -- Topic modeling -- Sentiment analysis -- Latent-class choice model -- Decision support; City planning -- Periodicals; Urban policy -- Periodicals; 711.4
• DOI: 10.1016/j.cities.2017.01.004
• Languages: English
• ISSNs: 0264-2751

Abstract

Abstract: Autonomous vehicles (AVs) have emerged as a transformative technology with the potential to both fundamentally improve lives in cities but also to exacerbate suburban sprawl, vehicle miles traveled and the associated greenhouse gas emissions. Are communities willing to adopt best practices that can lead to early adoption of more sustainable outcomes? This paper presents innovative means to analyze social preferences, demand for AVs, and the potential to resolve community concerns with integrated solutions. We discuss our comprehensive analysis of unstructured and structured data from a survey on AVs that was conducted by the Atlanta Regional Commission in 2015. We used topic modeling to synthesize the "topics" from 1540 comments. The topics captured Atlanta residents' concerns and suggestions about implementing AVs. Further, sentiment analysis revealed people's attitudes on the topics. Accordingly, we proposed an integration of AVs and transit-oriented development (TOD: the development of compact and mixed-use communities around high quality mass transit services within a 10-min walking distance). The second type of data is people's responses to multiple-choice questions about AVs and TOD, which we call structured data. Using latent-class analysis, we identified heterogeneity in preferences for AVs and TOD. More Atlanta residents are willing to live in transit-oriented communities than traditional automobile-dependent ones if AVs save time and improve productivity. This finding portends the future success of combining AVs with TOD and reaping the sustainable benefits of this transformative technology. Highlights: We illustrate a comprehensive approach to inform the adoption of autonomous vehicle. Topic model shows concerns/suggestions from Atlanta residents on autonomous vehicle. Integration of autonomous vehicles and transit-oriented development is needed. Our latent-class choice analysis confirms the market potential of this integration. Verification of the performance of this integration will be needed.