Advertisement

Public Transport

, Volume 10, Issue 2, pp 363–377 | Cite as

Using Twitter data for transit performance assessment: a framework for evaluating transit riders’ opinions about quality of service

  • N. Nima Haghighi
  • Xiaoyue Cathy LiuEmail author
  • Ran Wei
  • Wenwen Li
  • Hu Shao
Original Paper
  • 192 Downloads

Abstract

Social media platforms such as Facebook, Instagram, and Twitter have drastically altered the way information is generated and disseminated. These platforms allow their users to report events and express their opinions toward these events. The profusion of data generated through social media has proved to have the potential for improving the efficiency of existing traffic management systems and transportation analytics. This study complements existing literature by proposing a framework to evaluate transit riders’ opinion about quality of transit service using Twitter data. Although previous studies used keyword search to extract transit-related tweets, the extracted tweets can still be noisy and might not be relevant to transit quality of service at all. In this study, we leverage topic modeling, an unsupervised machine learning technique, to sift tweets that are relevant to the actual user experience of the transit system. Sentiment analysis is further performed based on the tweet-per-topic index we developed, to gauge transit riders’ feedback and explore the underlying reasons causing their dissatisfaction on the service. This framework can be potentially quite useful to transit agencies for user-oriented analysis and to assist with investment decision making.

Keywords

Topic modeling Latent Dirichlet allocation (LDA) Sentiment analysis Transit service performance Quality of transit service 

References

  1. Arias M, Arratia A, Xuriguera R (2013) Forecasting with Twitter data. ACM Trans Intell Syst Technol 5(1):1–24CrossRefGoogle Scholar
  2. Barreira N, Godinho P, Melo P (2013) Nowcasting unemployment rate and new car sales in South-western Europe with Google Trends. NETNOMICS Econ Res Electron Netw 14(3):129–165CrossRefGoogle Scholar
  3. Bernardo JM, Bayarri MJ, Berger JO, Dawid AP, Heckerman D, Smith AFM, West M (2003) The variational Bayesian EM algorithm for incomplete data: with application to scoring graphical model structures. Bayesian Stat 7:453–464Google Scholar
  4. Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993–1022Google Scholar
  5. Bose S, Saha U, Kar D, Goswami S, Nayak AK, Chakrabarti S (2017) RSentiment: a tool to extract meaningful insights from textual reviews. In: Proceedings of the 5th international conference on frontiers in intelligent computing: theory and applications, SingaporeGoogle Scholar
  6. Bughin J (2015) Google searches and Twitter mood: nowcasting telecom sales performance. NETNOMICS Econ Res Electron Netw 16(1–2):87–105CrossRefGoogle Scholar
  7. Cheng Z, Caverlee J, Lee KD, Sui DZ (2011) Exploring millions of footprints in location sharing services. International AAAI conference on web and social media (ICWSM), pp 81-88Google Scholar
  8. Cho E, Myers SA, Leskovec J (2011) Friendship and mobility: user movement in location-based social networks. In: Proceedings of the 17th ACM SIGKDD international conference on knowledge discovery and data mining. ACM: 1082–1090Google Scholar
  9. Collins C, Hasan S, Ukkusuri SV (2013) A novel transit rider satisfaction metric. J Public Transp 16(2):21–45CrossRefGoogle Scholar
  10. Farber S, Ritter B, Fu L (2016) Space–time mismatch between transit service and observed travel patterns in the Wasatch Front, Utah: a social equity perspective. Travel Behav Soc 4:40–48CrossRefGoogle Scholar
  11. Fayyaz SK, Liu XC, Porter RJ (2017) Dynamic transit accessibility and transit gap causality analysis. J Transp Geogr 59:27–39CrossRefGoogle Scholar
  12. Fu K, Nune R, Tao JX (2015) Social media data analysis for traffic incident detection and management. Transportation research board 94th annual meeting 15-4022, Washington, D.CGoogle Scholar
  13. Gao H, Tang J, Liu H (2012) Exploring social-historical ties on location-based social networks. In: International AAAI conference on web and social media (ICWSM). The AAAI Press, CaliforniaGoogle Scholar
  14. Golder SA, Macy MW (2011) Diurnal and seasonal mood vary with work, sleep and daylength across diverse cultures. Science 333(6051):1878–1881CrossRefGoogle Scholar
  15. Goldsmith S (2017) L.A.’s testing ground for transportation efficiency, Mar. 2016. http://www.governing.com/blogs/bfc/gov-los-angeles-transportation-efficiency-mobility-management.html. Accessed 20 Jul 2017
  16. Goodchild MF (2007) Citizens as sensors: the world of volunteered geography. GeoJournal 69(4):211–221CrossRefGoogle Scholar
  17. Hasan S, Zhan X, Ukkusuri SV (2013) Understanding urban human activity and mobility patterns using large-scale location-based data from online social media. In: Proceedings of the 2nd ACM international workshop on urban computing, pp 6:1–6:8Google Scholar
  18. Hornik K, Grün B (2011) Topicmodels: an R package for fitting topic models. J Stat Softw 40(13):1–30Google Scholar
  19. Kaplan AM, Haenlein M (2010) Users of the world, unite! The challenges and opportunities of Social Media. Bus Horiz 53(1):59–68CrossRefGoogle Scholar
  20. Kosala R, Adi E (2012) Harvesting real time traffic information from Twitter. Procedia Eng 50:1–11CrossRefGoogle Scholar
  21. Lindsay BR (2011) Social media and disasters: current uses, future options, and policy considerations. Congress research service 41987Google Scholar
  22. Liu B (2012) Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, vol 5, no 1. Morgan & Claypool PublishersGoogle Scholar
  23. Luong TT, Houston D (2015) Public opinions of light rail service in Los Angeles, an analysis using Twitter Data. iConference 2015 Proceedings, PhiladelphiaGoogle Scholar
  24. Maghrebi M, Abbasi A, Rashidi TH, Waller ST (2015) Complementing travel diary surveys with Twitter data: application of text mining techniques on activity location, type and time. 18th international conference on intelligent transportation systems (ITSC), Las Palmas, SpainGoogle Scholar
  25. Mai E, Hranac R (2013) Twitter interactions as a data source for transportation incidents. Presented at Transportation Research Board 92nd annual meeting, Washington, D.CGoogle Scholar
  26. Sakaki T, Okazaki M, Matsuo Y (2010) Earthquake shakes Twitter users: real-time event detection by social sensors. In: Proceedings of the 19th international conference on World Wide Web, Raleigh, North CarolinaGoogle Scholar
  27. Schweitzer L (2014) Planning and social media: a case study of public transit and stigma on Twitter. J Am Plan Assoc 80(3):218–238CrossRefGoogle Scholar
  28. Steiger E, Ellersiek T, Zipf A (2014) Explorative public transport flow analysis from uncertain social media data. In: Proceedings of the 3rd ACM SIGSPATIAL international workshop on crowd sourced and volunteered geographic information—GeoCrowd’14. New York, New York, ACM Press, pp 1–7Google Scholar
  29. Steur RJ (2015) Twitter as a spatio-temporal source for incident management. Master’s Thesis, Utrecht University, NetherlandsGoogle Scholar
  30. Tasse D, Hong JI (2014) Using social media data to understand cities. In: Proceedings of NSF workshop on big data and urban informatics. Carnegie Mellon University, Pittsburg, PennsylvaniaGoogle Scholar
  31. Tian Y, Zmud M, Chiu YC, Carey D, Dale J, Smarda D, Lehr R, James R (2016) Quality assessment of social media traffic reports—a field study in Austin, Texas. Transportation Research Board 95th annual meeting, No. 16-6852, Washington, D.CGoogle Scholar
  32. Transportation Research Board (2003) Transit capacity and quality of service manual. TCRP Report 100. National Academy Press, Washington, D.C.Google Scholar
  33. Ukkusuri S, Zhan X, Sadri A, Ye Q (2014) Use of social media data to explore crisis informatics: study of 2013 Oklahoma Tornado. Transp Res Rec J Transp Res Board 2459:110–118CrossRefGoogle Scholar
  34. Vision Zero (2016) High injury network. http://visionzero.lacity.org/high-injury-network/. Accessed 20 Jul 2017
  35. Wanichayapong N, Pruthipunyaskul W, Pattara-Atikom W, Chaovalit P (2011) Social-based traffic information extraction and classification. 2011 IEEE 11th international conference on ITS telecommunications, pp 107–112Google Scholar
  36. Wei R, Liu X, Wang L, Golub A, Farber S (2017) Evaluating public transit services for operational efficiency and access equity. J Transp Geogr 65:70–79CrossRefGoogle Scholar
  37. Yin Z, Fabbri D, Rosenbloom ST, Malin B (2015) A scalable framework to detect personal health mentions on Twitter. J Med Internet Res 17(6):e138CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Civil and Environmental EngineeringUniversity of UtahSalt Lake CityUSA
  2. 2.School of Public PolicyUniversity of California at RiversideRiversideUSA
  3. 3.School of Geographical Sciences and Urban PlanningArizona State UniversityTempeUSA

Personalised recommendations