Research Interest

Urban Analytics, Smart Cities, Intelligent Transport

While the new transport technologies are rolling out quickly, most transportation systems in cities are ill-prepared to embrace, let alone capitalize on the benefits from these new technologies. For instance, evidence shows that AVs technology would address the efficiency of road usage[1], but we are still figuring out methods for evaluating its feasibility, the policies associated with the technology and ethical and moral implications. Case studies on the deployment of AVs in both greenfield and brownfield areas are also lacking for understanding for how a fast-emerging transportation technology (such as AVs) can be integrated into metropolitan (e.g. Toronto, Singapore, New York) public transit systems and whether transport users will support or resist the change.

Studies have shown that attitudes influence travel behaviour [2]. Attitudes towards emerging technologies, for example, shared mobility and AVs, may indicate how mobility demands could be formed in different contexts of emerging transportation technologies[3]. Yet, attitudes studies are sidelined in favour of economic analysis and rational choice models in travel behaviour studies[4]. For the most part, these models assume population as homogenous. Clearly, different segments of the population have different mobility needs[5] [6], and they produce variegated demands and expectations for future urban mobility. Understanding the diverse attitudes can be decisive to make or break certain technologies. Dismissing these attitudes can misinform efforts to integrate public transit and emerging technologies in transportation planning.

Research objectives

I aim to implement advanced transport behavioural modelling methods to study the acceptance or resistance towards new transportation technologies. My future research can offer insights into the interplay among travel behaviour, attitudes (or preferences), and emerging transportation technologies that will better inform policies and planning—addressing open questions such as how to integrate different transport technologies, which infrastructures to be upgraded or left to ‘rot’. Choosing not to upgrade the infrastructures that will not be very useful in the future can free up public resources which can be redirected for addressing more pressing issues.



To model the complexity related to attitudes and transportation technologies, my research will incorporate behaviour modelling, data analytics, scenarios and sentiments analyses of emerging transportation technologies to model future urban mobility systems that integrate public transit, shared mobility and AVs[7]. My proposed research can be categorized briefly into three phases as follows:

  1. Explore attitudes and expectations using scenario planning exercise and sentiment analysis [8] (e.g. geotagged tweets) related to emerging transportation technologies.

  2. Analyze and curate ‘big’ heterogeneous mobility data generated from different sources such as smartphones, weather stations and smartcards in the context of different mobility options.

  3. Explore new methods and algorithms and design model specifications incorporating future scenarios, sentiment analysis, and mobility data.

First, I will apply network analysis to map actor’s coalitions, institutions, and other cross-scale linkages for emerging technologies and evaluate the residual effect (i.e. support or resist). The result will be substantiated by the outcomes from scenario and sentiment analyses pertaining to the relevant technologies. Second, I will innovate creative ways to process heterogeneous mobility data into critical information and knowledge (see e.g. weather and accidents[9]) that can be used to construct model specifications. Phase 1 & 2 of my research are inspired by Rob’s Kitchen’s article “Big data and human geography: opportunities, challenges and risks”[10] and other computational social scientists. Particularly, the work of Jennifer Pan in translating a large social media data into an understanding of political sentiments and what actions spurred by these sentiments[11] stands out. The final implementation is to build the simulation platform (e.g. agent-based model) incorporating all the curated data to evaluate the integration of new emerging transport technologies in public transit systems. Particularly, this simulation can model the effects of different technology portfolios, investment and policies assumptions under alternative scenarios.


[1] Metz, D., 2018. Developing Policy for Urban Autonomous Vehicles: Impact on Congestion. Urban Science, 2(2), p.33.

[2] Jensen, M., 1999. Passion and heart in transport—a sociological analysis on transport behaviour. Transport Policy, 6(1), pp.19-33.

[3] Kurniawan, J.H., Ong, C. and Cheah, L., 2018. Examining values and influences affecting public expectations of future urban mobility: A Singapore case study. Transport Policy, 66, pp.66-75.

[4] Kamargianni, M., Ben-Akiva, M. and Polydoropoulou, A., 2014. Incorporating social interaction into hybrid choice models. Transportation, 41(6), pp.1263-1285.

[5] Farber, S., Bartholomew, K., Li, X., Páez, A. and Habib, K.M.N., 2014. Assessing social equity in distance based transit fares using a model of travel behavior. Transportation Research Part A: Policy and Practice, 67, pp.291-303.

[6] Legrain, A., Buliung, R. and El-Geneidy, A.M., 2016. Travelling fair: Targeting equitable transit by understanding job location, sectorial concentration, and transit use among low-wage workers. Journal of Transport Geography, 53, pp.1-11.

[7] I posit that shared mobility and AVs will be so closely related, it’s like saying “if it’s an AV, it must be Uber.” But, I stand corrected.

[8] Wang, Y. and Taylor, J.E., 2018. Coupling sentiment and human mobility in natural disasters: a Twitter-based study of the 2014 South Napa Earthquake. Natural Hazards, 92(2), pp.907-925.

[9] Andrey, J., 2010. Long-term trends in weather-related crash risks. Journal of Transport Geography, 18(2), pp.247-258.

[10] Kitchin, R., 2013. Big data and human geography: Opportunities, challenges and risks. Dialogues in human geography, 3(3), pp.262-267.

[11] Although Jennifer Pan’s works do not relate to transportation research per se, her approaches are innovative and can be bridged to transportation research. Example of her work: King, G., Pan, J. and Roberts, M.E., 2013. How censorship in China allows government criticism but silences collective expression. American Political Science Review, 107(2), pp.326-343, uses curated social media to answer research questions.