[Research Contribution] Applying machine learning to analyze passenger satisfaction with public bus services in Ho Chi Minh city
12 November, 2026
Keywords: Machine learning, natural language processing, sentiment analysis, aspect-based sentiment analysis, public buses, passenger satisfaction, Ho Chi Minh city.
As urbanization accelerates and travel demand continues to grow, improving the quality of public transportation has become essential to achieving sustainable urban development. Passenger satisfaction provides valuable data for identifying shortcomings in service delivery. However, traditional survey methods often struggle to capture the full range of public opinions and emotions. In response to this challenge, a research team from UEH Mekong, University of Economics Ho Chi Minh City (UEH), applied machine learning and natural language processing to analyze 13,321 reviews of public bus services in Ho Chi Minh City. The study identified key factors influencing passenger satisfaction and proposed solutions to improve service quality.
Using passenger feedback data to evaluate public transportation quality
Passenger satisfaction is shaped by the comparison between initial expectations and actual service experiences. In public transportation, factors such as waiting time, service frequency, vehicle quality, and staff attitudes can all influence people’s decisions to continue using bus services.
The study applies the Expectation-Disconfirmation Paradigm (EDP) and the SERVQUAL model to examine the factors that shape service quality. In addition, the research team employs Aspect-Based Sentiment Analysis (ABSA), which identifies passengers’ attitudes toward specific service attributes rather than simply classifying feedback as positive or negative.
This approach is particularly relevant as online feedback continues to grow. Through machine learning and natural language processing techniques, written comments can be transformed into structured data, helping identify service issues and providing a basis for decision-making.
Analysis of 13,321 reviews: Dissatisfaction accounts for the largest share
The study uses 13,321 actual passenger reviews of public bus services in Ho Chi Minh City, collected between September 2022 and June 2025. The data were processed through several steps, including text normalization, word segmentation, stop-word removal, and conversion into numerical representations using Term Frequency–Inverse Document Frequency (TF-IDF).
To evaluate classification performance, the research team tested four supervised machine learning algorithms: Logistic Regression, Naïve Bayes, Support Vector Machine (SVM), and Random Forest. The results show that dissatisfied reviews accounted for the largest proportion, at 48.2% of all responses, while satisfied and neutral reviews represented 30.4% and 21.3%, respectively.
Among the four algorithms, SVM achieved the highest classification performance, with an accuracy of 96.1% and an F1-score of 0.960. Logistic Regression ranked second, with an accuracy of 92.3%, while offering faster inference time: approximately 0.031 seconds, compared with 1.828 seconds for SVM. These findings suggest that model selection should consider both classification accuracy and the practical processing requirements of the system.
Key challenges shaping passenger experiences
Aspect-based sentiment analysis reveals that drivers received the highest volume of feedback and also recorded a considerable proportion of negative comments. These comments primarily concerned driving skills, interpersonal behavior, and professionalism in serving passengers.
In addition, service attitudes, waiting times, and bus service frequency were identified as factors affecting the user experience. Vehicle quality and the performance of onboard staff and conductors also received feedback requiring attention. Although fewer comments concerned fares and the BusMap application, the data still reflected concerns about whether service quality justified the cost, as well as the convenience of digital tools supporting passengers.
These findings indicate that passenger satisfaction depends not only on vehicle conditions but also on service quality and operational reliability. Notably, analyzing passenger feedback enables transport authorities to identify specific issues that require priority attention, rather than relying solely on general service quality indicators.
Policy implications
Based on the research findings, the authors propose five groups of solutions to improve public bus services in Ho Chi Minh City:
First, strengthen the capacity of operational staff: Provide more training in communication skills, service attitudes, and professional responsibility for drivers, staff, and bus conductors.
Second, optimize routes and service frequency: Review operating schedules and adjust service frequency to reduce waiting times and improve punctuality.
Third, improve vehicle quality: Strengthen maintenance and upgrade buses to ensure cleanliness, comfort, and safety.
Fourth, enhance passenger support tools: Improve the BusMap application, keep route and operating-time information up to date, and make the service more accessible and user-friendly.
Fifth, apply data analytics to service quality monitoring: Establish a system for regularly collecting and analyzing passenger feedback to identify emerging issues early and help transport authorities make timely service adjustments.
Overall, the study demonstrates the potential of machine learning and natural language processing in analyzing large-scale passenger feedback. Rather than merely collecting opinions, these methods transform passenger experiences into valuable information for service management and improvement. The findings therefore highlight the potential of a data-driven approach to developing a more efficient, sustainable, and people-centered public transportation system.
View the full research paper “Applying Machine Learning to Analyze Passenger Satisfaction with Public Bus Services in Ho Chi Minh City” HERE.
Authors: Le My Trinh, Trinh Le Duy, Dr. Thai Kim Phung – University of Economics Ho Chi Minh City (UEH); Lam Thi Bich Ngan – VSC Entertainment and Communication Service Company Limited
This article is part of the series disseminating research and applied knowledge under the message “For a More Sustainable Mekong,” within the “Research Contribution For All” program conducted by UEH. UEH respectfully invites readers to stay tuned for the next edition of the UEH Research Insights newsletter.
News, photos: Authors, Department of Admissions – Communications UEH Mekong, Department of Communications and Partnerships UEH
Chia sẻ:
[Research Contribution] Co-innovating for a Sustainable Ocean Economy
12 December, 2025
[Podcast] Recommendations for University education development
14 February, 2025
[Podcast] Developing Vung Tau into a World-Class Tourism City
16 January, 2025
[Podcast] Postdigital Design Strategies for Media Art
6 January, 2025
[Podcast] NFTs – Artistic Innovation or Just a New Hype?
27 December, 2024
[Podcast] Boosting Employee Creativity with Constructive Feedback
23 November, 2024
[Podcast] “Dutch Disease” in Remittances and the Case of Vietnam
4 November, 2024
[Podcast] Latest approaches for sustainable universities
11 July, 2024
Data Law – Part 1: Necessity for a New Approach
18 May, 2024
Advertising Evaluation on Tiktok Platform
14 May, 2024
[Podcast] Advertising Evaluation on Tiktok Platform
13 May, 2024
Promoting Learner Autonomy in English Language Learning (Part 1)
24 November, 2023
ArtTech And Sustainable Development
27 October, 2023
Motivation of EFL Vietnamese Students in Economics-related Majors
12 October, 2023
Climate Change And Our Society: The Urgency Of Gender Inequality
12 October, 2023
People Analytics in Vietnam
10 March, 2022
Revolution in Experimental Economics
30 January, 2022
The Sharing Economy: Governance Issues in Vietnam
24 January, 2022
Employment Policy For Ho Chi Minh City in Post-social distancing Period
28 December, 2021
Lifelong learning at UEH: Towards a Sustainable University
28 December, 2021
Building a Decentralized Stock Market based on Blockchain Technology
24 December, 2021
Consumer price index from big data mining perspective (Big data)
17 November, 2021
Overview Of Digital Currency – Part 5: DIEM Private Stabilized Currency
11 November, 2021
