Deriving Knowledge from E-Scooter Riders’ Feedback at Pilot Study Stage: Case for a City in Ontario, Canada

Authors

  • Seun Daniel Oluwajana *

    Lead Transportation Analyst/Consultant, Mobility Scope Consulting, Edmonton, Alberta T6W4C6, Canada
  • Olubunmi Philip Oluwajana

    Department of Earth Sciences, Adekunle Ajasin University, Akungba Akoko, Ondo State 342111, Nigeria
  • Temitope Elizabeth Oguntelure

    Transportation Analyst, Mobility Scope Consulting, Akure, Ondo State 340001, Nigeria
  • Crystal Mingyue Wang

    Rail Systems Specialist, WSP, Thornhill, Ontario L3T 7Z6, Canada
  • Soha Saiyed

    Transportation Planner, R.J. Burnside & Associates Limited, Orangeville, Ontario L5N 8R9, Canada

DOI:

https://doi.org/10.55121/tdr.v2i2.301

Keywords:

E-scooter, User Generated Content, Riders’ Feedback, Text Mining, Opinion and Sentiment Analysis, YOLOv11, NPU

Abstract

This paper examines the sentiments and opinions of e-scooter riders in Windsor, Ontario, highlighting key issues and concerns they have expressed. It involved text mining of feedback collected over a six-month pilot program (May to October 2021) using dictionary-based analysis. Analysis of monthly word frequencies in rider feedback revealed fluctuations, with June, July, and August showing higher correlations with May—the initial pilot month—compared to September and October. This indicates a fading novelty associated with e-scooters in the city. Although monthly sentiments varied significantly, the overall sentiment in May and June remained positive. The most common words contributing to positive sentiment included fun, awesome, and nice, while negative sentiments were largely represented by words such as slow, broken, and throttle. Feedback reveals that riders primarily regard e-scooters as a source of leisure rather than functional transportation. Correlation analysis of words linked to negative sentiments identified terms like “flat-tire” and “broken throttle,” which emphasize significant concerns regarding e-scooter maintenance practices in Windsor. The findings underscore the need for a data-sharing policy and maintenance regulations while recommending a governance framework for e-scooters to ensure their sustainable benefits. It demonstrates that even with a limited feedback sample during the pilot phase of shared e-scooter implementation, dictionary-based opinion and sentiment analysis can yield valuable insights into rider concerns, guiding immediate policy needs and fostering the functional use of e-scooters as a transportation option.

References

[1] Latinopoulos, C., Patrier, A., Sivakumar, A., 2021. Planning for e-scooter use in metropolitan cities: A case study for Paris. Transportation Research Part D: Transport and Environment. 100, 103037. DOI: https://doi.org/10.1016/j.trd.2021.103037

[2] Kazemzadeh, K., Sprei, F., 2022. Towards an electric scooter level of service: A review and framework. Travel Behaviour and Society. 29, 149–164. DOI: https://doi.org/10.1016/j.tbs.2022.06.005

[3] Aman, J.J., Smith-Colin, J., Zhang, W., 2021. Listen to E-scooter riders: Mining rider satisfaction factors from app store reviews. Transportation Research Part D: Transport and Environment. 95, 102856. DOI: https://doi.org/10.1016/j.trd.2021.102856

[4] Wang, K., Qian, X., Fitch, D.T., et al., 2023. What travel modes do shared e-scooters displace? A review of recent research findings. Transport Reviews. 43(1), 5–31.

[5] Kong, V., Leszczynski, A., 2022. Dockless micromobility sharing in Calgary: A spatial equity comparison of e-bikes and e-scooters. Canadian Journal of Urban Research. 31(1), 97–110.

[6] Evans-Cowley, J.S., Griffin, G., 2012. Microparticipation with social media for community engagement in transportation planning. Transportation Research Record. 2307(1), 90–98.

[7] Dhini, A., Hardaya, I.S., Surjandari, I., 2017. Clustering and visualization of community complaints and proposals using text mining and geographic information system. Proceedings of the 2017 3rd International Conference on Science in Information Technology (ICSITech); 25 October 2017; Bandung, Indonesia. IEEE. pp. 132–137.

[8] Gao, Y., Chen, Y., Mu, L., et al., 2022. Measuring urban sentiments from social media data: a dual-polarity metric approach. Journal of Geographical Systems. 24(2), 199–221.

[9] Kapp, A., 2024. Collection, usage and privacy of mobility data in the enterprise and public administrations. Proceedings on Privacy Enhancing Technologies. 2022(4), 440–456. DOI: https://doi.org/10.48550/arXiv.2407.03732

[10] Skiera, B., Yan, S., Daxenberger, J., et al., 2022. Using information-seeking argument mining to improve service. Journal of Service Research. 25(4), 537–548.

[11] Field, C., Jon, I., 2021. E-scooters: A new smart mobility option? The case of Brisbane, Australia. Planning Theory & Practice. 22(3), 368–396.

[12] Yang, H., Huo, J., Bao, Y., et al., 2021. Impact of e-scooter sharing on bike sharing in Chicago. Transportation Research Part A: Policy and Practice. 154, 23–36.

[13] Hawa, L., Cui, B., Sun, L., et al., 2021. Scoot over: Determinants of shared electric scooter presence in Washington DC. Case Studies on Transport Policy. 9(2), 418–430.

[14] Bozzi, A.D., Aguilera, A., 2021. Shared E-scooters: A review of uses, health and environmental impacts, and policy implications of a new micro-mobility service. Sustainability. 13(16), 8676. DOI: https://doi.org/10.3390/su13168676

[15] Jiao, J., Bai, S., Choi, S.J., 2021. Understanding e-scooter incidents patterns in street network perspective: a case study of travis county, Texas. Sustainability. 13(19), 10583. DOI: https://doi.org/10.3390/su131910583

[16] Dias, G., Arsenio, E., Ribeiro, P., 2021. The role of shared e-scooter systems in urban sustainability and resilience during the covid-19 mobility restrictions. Sustainability. 13(13), 7084. DOI: https://doi.org/10.3390/su13137084

[17] Glavić, D., Trpković, A., Milenković, M., et al., 2021. The e-scooter potential to change urban mobility—Belgrade case study. Sustainability. 13(11), 5948. DOI: https://doi.org/10.3390/su13115948

[18] Lo, D., Mintrom, C., Robinson, K., et al., 2020. Shared micromobility: The influence of regulation on travel mode choice. New Zealand Geographer. 76(2), 135–146.

[19] Gebhardt, L., Wolf, C., Seiffert, R., 2021. "I'll take the E-scooter instead of my car"—The potential of E-scooters as a substitute for car trips in Germany. Sustainability. 13(13), 7361. DOI: https://doi.org/10.3390/su13137361

[20] Reck, D.J., Haitao, H., Guidon, S., et al., 2021. Explaining shared micromobility usage, competition and mode choice by modelling empirical data from Zurich, Switzerland. Transportation Research Part C: Emerging Technologies. 124, 102947. DOI: https://doi.org/10.1016/j.trc.2020.102947

[21] Almannaa, M.H., Alsahhaf, F.A., Ashqar, H.I., et al., 2021. Perception analysis of E-scooter riders and non-riders in Riyadh, Saudi Arabia: Survey outputs. Sustainability. 13(2), 863. DOI: https://doi.org/10.3390/su13020863

[22] Sikka, N., Vila, C., Stratton, M., et al., 2019. Sharing the sidewalk: A case of E-scooter related pedestrian injury. The American Journal of Emergency Medicine. 37(9), 1807.e5–1807.e7.

[23] Merlin, L.A., Yan, X., Xu, Y., et al., 2021. A segment-level model of shared, electric scooter origins and destinations. Transportation Research Part D: Transport and Environment. 92, 102709. DOI: https://doi.org/10.1016/j.trd.2021.102709

[24] Bai, S., Jiao, J., 2022. From shared micro-mobility to shared responsibility: Using crowdsourcing to understand dockless vehicle violations in Austin, Texas. Journal of Urban Affairs. 44(9), 1341–1353.

[25] Ali, F., Kwak, D., Khan, P., et al., 2019. Transportation sentiment analysis using word embedding and ontology-based topic modeling. Knowledge-Based Systems. 174, 27–42. DOI: https://doi.org/10.1016/j.knosys.2019.02.033

[26] Hao, J., Zhu, J., Zhong, R., 2015. The rise of big data on urban studies and planning practices in China: Review and open research issues. Journal of Urban Management. 4(2), 92–124. DOI: https://doi.org/10.1016/j.jum.2015.11.002

[27] Abbasi, A., Rashidi, T.H., Maghrebi, M., et al., 2015. Utilising location based social media in travel survey methods: bringing Twitter data into the play. Proceedings of the 8th ACM SIGSPATIAL International Workshop on Location-Based Social Networks; 3 November 2015; Seattle, WA, USA. ACM. pp. 1–9.

[28] Zhu, L., Yu, F.R., Wang, Y., et al., 2018. Big data analytics in intelligent transportation systems: A survey. IEEE Transactions on Intelligent Transportation Systems. 20(1), 383–398. DOI: https://doi.org/10.1109/TITS.2018.2815678

[29] Lin, C., Wang, G., 2017. Failure cause extraction of railway switches based on text mining. Proceedings of the 2017 International Conference on Computer Science and Artificial Intelligence; 5 December 2017; Shanghai, China. ACM. pp. 237–241. DOI: https://doi.org/10.1145/3168390.3168402

[30] Choi, S., Ko, J., Kim, D., 2021. Investigating commuters' satisfaction with public transit: A latent class modeling approach. Transportation Research Part D: Transport and Environment. 99, 103015. DOI: https://doi.org/10.1016/j.trd.2021.103015

[31] Sai, F., 2019. Survey of Sustainable Logistics Services via Text Mining. Journal of Mechanics Engineering and Automation. 9(3). DOI: https://doi.org/10.17265/2159-5275/2019.03.004

[32] Shokouhyar, S., Shokoohyar, S., Sobhani, A., et al., 2021. Shared mobility in post-COVID era: New challenges and opportunities. Sustainable Cities and Society. 67, 102714. DOI: https://doi.org/10.1016/j.scs.2021.102714

[33] Ridhwan, K.M., Hargreaves, C.A., 2021. Leveraging Twitter data to understand public sentiment for the COVID-19 outbreak in Singapore. International Journal of Information Management Data Insights. 1(2), 100021. DOI: https://doi.org/10.1016/j.jjimei.2021.100021

[34] Yang, H., Ma, Q., Wang, Z., et al., 2020. Safety of micro-mobility: Analysis of E-Scooter crashes by mining news reports. Accident Analysis & Prevention. 143, 105608. DOI: https://doi.org/10.1016/j.aap.2020.105608

[35] Silge, J., Robinson, D., 2017. Text Mining with R: A Tidy Approach. O'Reilly: Boston, MA, USA. pp. 1–193.

[36] Lloyd, M., 2022. Weaving fun and functionality. A study of everyday urban e-scootering. Etnografia e Ricerca Qualitativa. 15(2), 241–262. DOI: https://doi.org/10.3240/103668

[37] Krier, C., Chrétien, J., Lagadic, M., et al., 2021. How do shared dockless e-scooter services affect mobility practices in Paris? A survey-based estimation of modal shift. Transportation Research Record. 2675(11), 291–304.

[38] Bieliński, T., Ważna, A., 2020. Electric scooter sharing and bike sharing user behaviour and characteristics. Sustainability. 12(22), 9640. DOI: https://doi.org/10.3390/su12229640

[39] Kjærup, M., Skov, M.B., Van Berkel, N., 2021. E-scooter sustainability–a clash of needs, perspectives, and experiences. Proceedings of the IFIP Conference on Human-Computer Interaction; 26 August 2021; Bari, Italy. Springer: Cham, Switzerland. pp. 365–383.

[40] Severengiz, S., Schelte, N., Bracke, S., 2021. Analysis of the environmental impact of e-scooter sharing services considering product reliability characteristics and durability. Procedia CIRP. 96, 181–188.

[41] Kopplin, C.S., Brand, B.M., Reichenberger, Y., 2021. Consumer acceptance of shared e-scooters for urban and short-distance mobility. Transportation Research Part D: Transport and Environment. 91, 102680. DOI: https://doi.org/10.1016/j.trd.2020.102680

[42] Dibaj, S., Hosseinzadeh, A., Mladenović, M.N., et al., 2021. Where have shared e-scooters taken us so far? A review of mobility patterns, usage frequency, and personas. Sustainability. 13(21), 11792. DOI: https://doi.org/10.3390/su132111792

Downloads

Issue

Vol. 2 No. 2 (November 2024): In progress

Section

Article