Skip to main content
Log in

Five-star transportation: using online activity reviews to examine mode choice to non-work destinations

  • Published:
Transportation Aims and scope Submit manuscript


Information and communication technologies are generating unprecedented quantities of data with potential applications in transportation planning and research. Because of their focus on non-work activities, crowdsourced activity reviews such as Yelp reviews have the potential to inform how individuals make travel choices to a range of activities with significant economic impacts. Substantial numbers of Yelp reviews include transportation content, including mode choices. I use content analysis to extract and understand statements on mode from a dataset of more than 225,000 Yelp reviews in the Phoenix metropolitan area. Spatial analysis of the results shows that access to non-work destinations varies significantly by mode across the region and within neighborhoods. The findings address ongoing questions in accessibility research, including preferences for transit around rail stations and local variability in walking preferences. Yelp data do not replace travel surveys, but they provide significantly more information and spatial detail on mode choice to many non-work destinations. Though this and similar datasets show promise for several applications in transportation planning and research, the issues of potential sampling biases and data ownership and access must also be addressed for these data to become widespread tools for practioners and researchers.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others


  1. A Ripley’s K Function analysis of clustering of review locations found statistically significant clustering (p > 0.05) at scales from 0.5 to 5 km.

  2. Terms were selected based on their ability to capture the primary travel modes in Phoenix—driving and parking, walking, transit, and biking. The terms in Table 1 are the most frequently appearing words associated with these modes, leaving out terms like “park” or “sidewalk” that may have alternate interpretations.

  3. One-way ANOVA confirms that mode shares for “rail” and “parking” are significantly different across distance bands (p > 0.001).

  4. Parking mentions may decrease past 750 m because, beyond this distance, the need to recommend where or how to park also decreases. The light rail line was built along a relatively dense commercial corridor, and lower densities further from the corridor may also reduce concerns about parking availability. In further research, an examination of local activity density, as well as parking availability and utilization at block and neighborhood scales, could help shed light on whether parking recommendations are correlated with parking policies and utilization rates.

  5. Intriguingly, walking is also correlated with another facet of local station areas, destination density. In order to compare among the 28 light rail station areas along the Phoenix Metro system, a correlation analysis examined the relationship of mode to the density of Yelp-listed businesses within the area. For the correlation analysis, station areas are defined as an area with a radius of 750 m around each station. This value is based upon the findings illustrated in Fig. 2, highlighting that review with rail content fall to a minimum at this point. This measure of destination density varies significantly among the station areas, from a 4 to 79 businesses per sq km, with a median of 15 businesses per sq km. In previous research, destination density has been significantly correlated with non-auto travel, and measures like WalkScore rely upon destination density to calculate walkability (Ewing and Cervero 2010; Manaugh and El-Geneidy 2011). Only walking showed a significant correlation with business density—0.4691 (p = 0.0118).


  • Andrienko, G., Andrienko, N., Bosch, H., Ertl, T., Fuchs, G., Jankowski, P., Thom, D.: Thematic patterns in georeferenced tweets through space-time visual analytics. Comput. Sci. Eng. 15, 72–82 (2013)

    Article  Google Scholar 

  • Batty, M., et al.: Smart cities of the future. Eur. Phys. J. Spec. Top. 214, 481–518 (2012)

    Article  Google Scholar 

  • Becker, R.A., Caceres, R., Hanson, K., Loh, J.M., Urbanek, S., Varshavsky, A., Volinsky, C.: A tale of one city: using cellular network data for urban planning. IEEE Pervasive Comput. 10, 18–26 (2011)

    Article  Google Scholar 

  • Ben-Elia, E., Alexander, B., Hubers, C., Ettema, D.: Activity fragmentation, ICT and travel: an exploratory path analysis of spatiotemporal interrelationships. Transp. Res. (2014). doi:10.1016/j.tra.2014.03.016

    Google Scholar 

  • Bertot, J.C., Choi, H.: Big data and e-government: issues, policies, and recommendations. In: Proceedings of the 14th Annual International Conference on Digital Government Research, ACM, pp. 1–10 (2013)

  • Boyles, J.L., Smith, A., Madden, M.: Privacy and Data Management on Mobile Devices. Pew Internet & American Life Project, Washington, D.C. (2012)

    Google Scholar 

  • Calabrese, F., Colonna, M., Lovisolo, P., Parata, D., Ratti, C.: Real-time urban monitoring using cell phones: a case study in Rome. IEEE Trans. Intell. Transp. Syst. 12, 141–151 (2011). doi:10.1109/TITS.2010.2074196

    Article  Google Scholar 

  • Castells, M.: The Rise of the Network Society: The Information Age: Economy, Society, and Culture, vol. 1. Wiley, New York (2011)

    Google Scholar 

  • Chambers, R.L., Skinner, C.J.: Analysis of Survey Data. Wiley, New York (2003)

    Book  Google Scholar 

  • Chatman, D.G.: Does TOD need the T? J. Am. Plan. Assoc. 79, 17–31 (2013). doi:10.1080/01944363.2013.791008

    Article  Google Scholar 

  • Cheng, Z., Caverlee, J., Lee, K., Sui, D.Z.: Exploring millions of footprints in location sharing services. In: Proceedings of ICWSM, pp. 81–88 (2011)

  • Dodds, P.S., Harris, K.D., Kloumann, I.M., Bliss, C.A., Danforth, C.M.: Temporal patterns of happiness and information in a global social network: hedonometrics and Twitter. PLoS ONE 6, e26752 (2011). doi:10.1371/journal.pone.0026752

    Article  Google Scholar 

  • Ewing, R., Cervero, R.: Travel and the built environment. J. Am. Plan. Assoc. 76, 265–294 (2010). doi:10.1080/01944361003766766

    Article  Google Scholar 

  • Fink, C.: More Than Just the “Loser Cruiser”? An Ethnographic Study of the Social Life on Buses. University of California, Los Angeles (2012)

    Google Scholar 

  • Higuchi K (2014) KH Coder, 2b31 edn.,

  • Kaufman, S.M.: Co-monitoring for Transit Management: Using Web-Based Rider Input for Transit Management. Rudin Center for Transportation, New York (2014)

    Google Scholar 

  • Kelley, M.: Urban experience takes an informational turn: mobile internet usage and the unevenness of geosocial activity. GeoJournal 79, 15–29 (2014). doi:10.1007/s10708-013-9482-1

    Article  Google Scholar 

  • Krippendorff, K.: Content Analysis: An Introduction to its Methodology. Sage, Beverly Hills (2012)

    Google Scholar 

  • Lu, Y., Liu, Y.: Pervasive location acquisition technologies: opportunities and challenges for geospatial studies. Comput. Environ. Urb. Syst. 36, 105–108 (2012). doi:10.1016/j.compenvurbsys.2012.02.002

    Article  Google Scholar 

  • Lynch, K.: The Image of the City. Technology Press, Cambridge (1960)

    Google Scholar 

  • Lyons, G., Avineri, E., Farag, S., Herman, R.: Strategic review of travel information research. Technical Report. Department for Transport, London (2007)

  • Manaugh, K., El-Geneidy, A.: Validating walkability indices: how do different households respond to the walkability of their neighborhood? Transp. Res. 16, 309–315 (2011). doi:10.1016/j.trd.2011.01.009

    Google Scholar 

  • Markov, Z., Larose, D.T.: Data Mining the Web: Uncovering Patterns in Web Content, Structure, and Usage. Wiley, New York (2007)

    Book  Google Scholar 

  • Milam, R.T., Stanek, D., Jackson, K.: The first penguin through the data ice hole: using cell phone and GPS data to improve integrated models. In: Managing Operational Performance. Exceeding Expectations. 2012 ITE Technical Conference and Exhibit, 2012

  • Minaei, N.: Do modes of transportation and GPS affect cognitive maps of Londoners? Transp. Res. 70, 162–180 (2014). doi:10.1016/j.tra.2014.10.008

    Google Scholar 

  • Mondschein, A., Blumenberg, E., Taylor, B.D.: Accessibility and cognition: the effect of transport mode on spatial knowledge. Urb. Stud. 47, 845–866 (2010)

    Article  Google Scholar 

  • Neirottim, P., De Marco, A., Cagliano, A.C., Mangano, G., Scorrano, F.: Current trends in smart city initiatives: some stylised facts. Cities 38, 25–36 (2014). doi:10.1016/j.cities.2013.12.010

    Article  Google Scholar 

  • Nelson, A.: Office rent premiums with respect to distance from light rail transit stations in Dallas and Denver. Paper presented at the 94th Annual Meeting of the Transportation Reseach Board, Washington, DC (2015)

  • Noulas, A., Scellato, S., Lambiotte, R., Pontil, M., Mascolo, C.: A tale of many cities: universal patterns in human urban mobility. PLoS ONE 7, e37027 (2012). doi:10.1371/journal.pone.0037027

    Article  Google Scholar 

  • Schweitzer, L.: Planning and social media: a case study of public transit and stigma on Twitter. J. Am. Plan. Assoc. 80, 218–238 (2014). doi:10.1080/01944363.2014.980439

    Article  Google Scholar 

  • Townsend, A.M.: Smart Cities: Big Data, Civic Hackers, and the Quest for a New Utopia. WW Norton & Company, Cambridge (2013)

    Google Scholar 

  • U.S. Census Bureau: Survey of business owners. (2007). Accessed 13 Jan 2015

  • U.S. Census Bureau: American community survey, 2013 1-year estimates. (2013). Accessed 13 Jan 2015

  • Waters, S., Ackerman, J.: Exploring privacy management on Facebook: motivations and perceived consequences of voluntary disclosure. J. Comput. Med. Commun. 17, 101–115 (2011)

    Article  Google Scholar 

  • Williams, S., Saldarriaga, J.F., Bullen, G., Tan, F., Younse, N., Valentini, B. We are here now (2011). Accessed May 13, 2014

  • Wu, L., Zhi, Y., Sui, Z., Liu, Y.: Intra-urban human mobility and activity transition: evidence from social media check-in data. PLoS ONE 9, e97010 (2014). doi:10.1371/journal.pone.0097010

    Article  Google Scholar 

  • Ye, Q., Law, R., Gu, B., Chen, W.: The influence of user-generated content on traveler behavior: an empirical investigation on the effects of e-word-of-mouth to hotel online bookings. Comput. Hum. Behav. 27, 634–639 (2011)

    Article  Google Scholar 

  • Yelp (2012) Terms of Service. Accessed May 14, 2014 2014

  • Yelp (2013) FAQ. Accessed July 31 2013

Download references


I am deeply grateful to the anonymous reviewers of this article for their helpful comments. Thanks also to Nathan Epstein and Nicholas Hutchinson for their efforts on this study.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Andrew Mondschein.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Mondschein, A. Five-star transportation: using online activity reviews to examine mode choice to non-work destinations. Transportation 42, 707–722 (2015).

Download citation

  • Published:

  • Issue Date:

  • DOI: