Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis
Despite the excitement around electric automobiles, Electric Vehicles (EVs) in Malaysia are still relatively new compared to more advanced markets such as European countries. To understand Malaysian acceptance and perception of EVs, this study uses sentiment analysis to ascertain whether Malaysians...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universiti Kebangsaan Malaysia
2025
|
| Subjects: | |
| Online Access: | https://umpir.ump.edu.my/id/eprint/45339/ |
| _version_ | 1848827388492775424 |
|---|---|
| author | Nor Farawahida, Abdullah Nur Haizum, Abd Rahman |
| author_facet | Nor Farawahida, Abdullah Nur Haizum, Abd Rahman |
| author_sort | Nor Farawahida, Abdullah |
| building | UMP Institutional Repository |
| collection | Online Access |
| description | Despite the excitement around electric automobiles, Electric Vehicles (EVs) in Malaysia are still relatively new compared to more advanced markets such as European countries. To understand Malaysian acceptance and perception of EVs, this study uses sentiment analysis to ascertain whether Malaysians view and utilise EVs positively or negatively. The dataset is scrapped data collected from comments on YouTube with Term Frequency-Inverse Document Frequency (TF-IDF) as the feature extraction method. The machine learning algorithm, support vector machine (SVM), is then created to automatically identify and classify comments about EV acceptance and perception. Key performance indicators, including accuracy, precision, and recall percentages, are used to assess the algorithm's performance. Results reveal that for the sentiment distribution, there is 55% positive and only 14% negative sentiment, while the remaining is neutral. The main concerns identified are battery, charging station, and price. The classification was further analysed, and the result suggests that SVM with TF-IDF feature extraction offered 85.18% accuracy in classifying the sentiment. The result of this study provides nuanced insights into public opinions regarding EVs in Malaysia by seamlessly integrating machine learning and sentiment analysis. The findings will have substantial implications for researchers in the sustainable transportation sector, policymakers, and industry stakeholders. |
| first_indexed | 2025-11-15T03:59:55Z |
| format | Article |
| id | ump-45339 |
| institution | Universiti Malaysia Pahang |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T03:59:55Z |
| publishDate | 2025 |
| publisher | Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | ump-453392025-08-11T08:06:55Z https://umpir.ump.edu.my/id/eprint/45339/ Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis Nor Farawahida, Abdullah Nur Haizum, Abd Rahman QA Mathematics TJ Mechanical engineering and machinery TK Electrical engineering. Electronics Nuclear engineering Despite the excitement around electric automobiles, Electric Vehicles (EVs) in Malaysia are still relatively new compared to more advanced markets such as European countries. To understand Malaysian acceptance and perception of EVs, this study uses sentiment analysis to ascertain whether Malaysians view and utilise EVs positively or negatively. The dataset is scrapped data collected from comments on YouTube with Term Frequency-Inverse Document Frequency (TF-IDF) as the feature extraction method. The machine learning algorithm, support vector machine (SVM), is then created to automatically identify and classify comments about EV acceptance and perception. Key performance indicators, including accuracy, precision, and recall percentages, are used to assess the algorithm's performance. Results reveal that for the sentiment distribution, there is 55% positive and only 14% negative sentiment, while the remaining is neutral. The main concerns identified are battery, charging station, and price. The classification was further analysed, and the result suggests that SVM with TF-IDF feature extraction offered 85.18% accuracy in classifying the sentiment. The result of this study provides nuanced insights into public opinions regarding EVs in Malaysia by seamlessly integrating machine learning and sentiment analysis. The findings will have substantial implications for researchers in the sustainable transportation sector, policymakers, and industry stakeholders. Universiti Kebangsaan Malaysia 2025-06 Article PeerReviewed pdf en https://umpir.ump.edu.my/id/eprint/45339/1/2025%20Consumer%20Acceptance%20and%20Perceptions%20of%20Electric%20Vehicles%20in%20Malaysia%20Using%20Sentiment%20Analysis.pdf Nor Farawahida, Abdullah and Nur Haizum, Abd Rahman (2025) Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis. Journal of Quality Measurement and Analysis, 21 (2). pp. 41-51. ISSN 1823-5670. (Published) https://doi.org/10.17576/jqma.2102.2025.04 https://doi.org/10.17576/jqma.2102.2025.04 https://doi.org/10.17576/jqma.2102.2025.04 |
| spellingShingle | QA Mathematics TJ Mechanical engineering and machinery TK Electrical engineering. Electronics Nuclear engineering Nor Farawahida, Abdullah Nur Haizum, Abd Rahman Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis |
| title | Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis |
| title_full | Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis |
| title_fullStr | Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis |
| title_full_unstemmed | Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis |
| title_short | Consumer acceptance and perceptions of electric vehicles in Malaysia using sentiment analysis |
| title_sort | consumer acceptance and perceptions of electric vehicles in malaysia using sentiment analysis |
| topic | QA Mathematics TJ Mechanical engineering and machinery TK Electrical engineering. Electronics Nuclear engineering |
| url | https://umpir.ump.edu.my/id/eprint/45339/ https://umpir.ump.edu.my/id/eprint/45339/ https://umpir.ump.edu.my/id/eprint/45339/ |