SARENDRA, MUHAMMAD BAGASWARA (2025) ANALISIS SENTIMEN MOBIL LISTRIK TERHADAP MINAT MASYARAKAT DENGAN ALGORITMA NAIVE BAYES, SUPPORT VECTOR MACHINE, DAN METODE CRISP-DM. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (431kB) | Preview |
|
![]() |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (44kB) |
|
![]() |
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (303kB) |
|
![]() |
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (50kB) |
|
![]() |
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (1MB) |
|
![]() |
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (38kB) |
|
![]() |
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (95kB) |
|
![]() |
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (1MB) |
Abstract
The increasing use of fossil fuel-powered vehicles has driven the development of electric cars as an environmentally friendly solution to reduce greenhouse gas emissions. This study aims to map Indonesian public opinion on electric cars and to compare the effectiveness of the Naive Bayes and SVM algorithms in sentiment analysis using a machine learning approach within the CRISP-DM framework. The data utilized in this study were gathered from 7,962 tweets on X (Twitter). The analysis results indicate a dominance of positive sentiment, influenced by government subsidies, environmental image, cost efficiency, and technological advancements. On the other hand, negative sentiment reflects concerns over the limited charging infrastructure, high prices, battery quality, and environmental impacts of nickel mining. Model performance evaluation shows that SVM significantly outperforms Naive Bayes, achieving an accuracy of 97.63% and an F1-score of 97.70%, compared to Naive Bayes with an accuracy of 88.9% and an F1-score of 88.03%. These findings suggest that SVM is a more optimal algorithm for sentiment classification of public opinion regarding electric cars. The outcomes of this research are expected to serve as a reference for government and industry stakeholders in formulating more effective strategies to promote the adoption of electric cars in Indonesia. Keywords: Sentiment Analysis, X (Twitter), Electric Cars, Naive Bayes, Support Vector Machine Tingginya penggunaan bahan bakar fosil pada moda transportasi mendorong lahirnya inovasi mobil listrik sebagai alternatif ramah lingkungan untuk menurunkan emisi gas rumah kaca. Penelitian ini bertujuan untuk memetakan opini masyarakat Indonesia terhadap mobil listrik serta mengevaluasi performa algoritma Naive Bayes dan SVM pada analisis sentimen berbasis machine learning, dengan menggunakan alur kerja CRISP-DM. Data yang digunakan diperoleh dari 7.962 tweet di jejaring sosial X (Twitter). Hasil analisis menunjukkan dominasi sentimen positif yang dipengaruhi oleh subsidi pemerintah, citra ramah lingkungan, efisiensi biaya, dan kemajuan teknologi. Di sisi lain, sentimen negatif mengindikasikan kekhawatiran terhadap keterbatasan infrastruktur pengisian daya, harga yang tinggi, kualitas baterai, serta dampak lingkungan dari penambangan nikel. Evaluasi performa model menunjukkan bahwa SVM unggul secara signifikan dengan akurasi 97,63% dan F1-score 97,70%, sedangkan Naive Bayes mencatat akurasi 88,9% dan F1-score 88,03%. Temuan ini mengindikasikan bahwa SVM merupakan algoritma yang lebih optimal dalam klasifikasi sentimen terhadap opini publik mengenai mobil listrik. Luaran dari penelitian ini diharapkan dapat berperan sebagai rujukan bagi instansi pemerintah dan pihak industri dalam merumuskan strategi yang lebih tepat untuk memperluas adopsi mobil listrik di Indonesia. Kata kunci: Analisis Sentimen, X (Twitter), Mobil Listrik, Naïve Bayes, Support Vector Machine
Actions (login required)
![]() |
View Item |