Sentiment analysis of electric vehicle feedback on social media in Vietnam : a case study of Vinfast | |
| Author | Nguyen Hoang Viet |
| Call Number | AIT PJPR PMDS no.25-06 |
| Subject(s) | Online social networks--Data processing--Vietnam--Case studies Electric vehicles--Public opinion--Data processing--Vietnam--Case studies Sentiment analysis Natural language processing (Computer science) |
| Note | A project report submitted in partial fulfillment of the requirements for the Degree of Master of Science (Professional) in Data Science and Artificial Intelligence Applications |
| Publisher | Asian Institute of Technology |
| Abstract | This investigation presents a systematic examination of opinion mining techniques applied to Vietnamese electric vehicle discourse on social media platforms, utilizing VinFast as the empirical context. The research addresses distinctive linguistic and cultural complexities inherent to Vietnamese digital communication. Given Facebook's dominant position in Vietnam's social media landscape, robust analytical tools are essential for interpreting public attitudes toward electric mobility and automotive wỏ.Our methodology explores multiple natural language processing architectures specifically adapted for Vietnamese textual characteristics, encompassing preprocessing protocols designed to handle diacritical variations, colloquial expressions, and informal register common in social network discourse. The investigation comparatively evaluates classical ML algorithms, neural network architectures, and transformer-based frameworks. Empirical validation on 15,330 comments reveals that Support Vector Machine (SVM) implementations with TF-IDF feature extraction achieve optimal performance (F1-score: 94.28%), surpassing complex transformer architectures due to the keyword-centric and brevity characteristics of social media text. Our corpus comprises over 15,330 Vietnamese Facebook posts concentrated on the electric vehicle sector, with VinFast serving as the primary analytical case. The investigation addresses core challenges including Vietnamese-English code-mixing, emoji-mediated sentiment expression, and culturally-contextualized opinion interpretation. |
| Year | 2025 |
| Type | Project |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Professional Master in Data Science and Artificial Intelligence Applications (PMDS) |
| Chairperson(s) | Chaklam Silpasuwanchai; |
| Examination Committee(s) | Chantri Polprasert;Vatcharaporn Esichaikul; |
| Degree | Master of Science (Professional) - Asian Institute of Technology, 2025 |