Febrianda, Larasati (2025) ANALISIS SENTIMEN PADA MEDIA SOSIAL X TERHADAP PROGRAM MAKAN SIANG GRATIS MENGGUNAKAN ALGORITMA NAÏVE BAYES CLASSIFIER DAN SUPPORT VECTOR MACHINE. S1 thesis, Universitas Mercu Buana Jakarta - Menteng.
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (COVER)
41520120011-LARASATIFEBRIANDA-01 Cover - LARASATI FEBRIANDA.pdf Download (432kB) |
|
Text (BAB I)
41520120011-LARASATIFEBRIANDA-02 Bab 1 - LARASATI FEBRIANDA.pdf Restricted to Registered users only Download (217kB) |
|
Text (BAB II)
41520120011-LARASATIFEBRIANDA-03 Bab 2 - LARASATI FEBRIANDA.pdf Restricted to Registered users only Download (425kB) |
|
Text (BAB III)
41520120011-LARASATIFEBRIANDA-04 Bab 3 - LARASATI FEBRIANDA.pdf Restricted to Registered users only Download (298kB) |
|
Text (BAB IV)
41520120011-LARASATIFEBRIANDA-05 Bab 4 - LARASATI FEBRIANDA.pdf Restricted to Registered users only Download (983kB) |
|
Text (BAB V)
41520120011-LARASATIFEBRIANDA-06 Bab 5 - LARASATI FEBRIANDA.pdf Restricted to Registered users only Download (177kB) |
|
Text (DAFTAR PUSTAKA)
41520120011-LARASATIFEBRIANDA-08 Daftar Pustaka - LARASATI FEBRIANDA.pdf Restricted to Registered users only Download (165kB) |
|
Text (LAMPIRAN)
41520120011-LARASATIFEBRIANDA-09 Lampiran - LARASATI FEBRIANDA.pdf Restricted to Registered users only Download (489kB) |
Abstract
Penelitian ini menganalisis sentimen publik terhadap Program Makan Siang Gratis yang menjadi sorotan di media sosial, khususnya platform X. Dua algoritma machine learning, yaitu Naïve Bayes Classifier dan Support Vector Machine (SVM), digunakan untuk mengkategorikan sentimen publik ke dalam kelas positif, negatif, dan netral. Data dikumpulkan melalui teknik crawling menggunakan Tweet-Harvest dan diolah melalui preprocessing untuk meningkatkan akurasi analisis. Untuk mengatasi ketidakseimbangan data, teknik SMOTE diterapkan, dan evaluasi model dilakukan menggunakan confusion matrix. Hasil penelitian menunjukkan bahwa SVM lebih akurat dibandingkan Naïve Bayes, baik sebelum maupun sesudah SMOTE. Sebelum SMOTE, SVM mencapai akurasi 88%, sementara Naïve Bayes 87%. Setelah SMOTE, SVM tetap konsisten di 87%, sedangkan Naïve Bayes menurun ke 72%. SVM juga lebih baik mengenali kelas minoritas (negatif dan netral), meskipun keduanya masih cenderung bias terhadap kelas mayoritas (positif). Penelitian ini menyimpulkan bahwa SVM unggul dalam analisis sentimen dengan data tidak seimbang, terutama setelah penerapan SMOTE. Hasil analisis menunjukkan bahwa persepsi masyarakat terhadap Program Makan Siang Gratis sebagian besar positif. This study analyzes public sentiment towards the Free Lunch Program that has been highlighted on social media, especially platform X. Two machine learning algorithms, namely Naïve Bayes Classifier and Support Vector Machine (SVM), are used to categorize public sentiment into positive, negative, and neutral classes. Data is collected through a crawling technique using Tweet-Harvest and processed through preprocessing to improve the accuracy of the analysis. To overcome data imbalance, the SMOTE technique is applied, and model evaluation is carried out using a confusion matrix. The results show that SVM is more accurate than Naïve Bayes, both before and after SMOTE. Before SMOTE, SVM achieved an accuracy of 88%, while Naïve Bayes was 87%. After SMOTE, SVM remained consistent at 87%, while Naïve Bayes decreased to 72%. SVM is also better at recognizing minority classes (negative and neutral), although both still tend to be biased towards the majority class (positive). This study concludes that SVM excels in sentiment analysis with imbalanced data, especially after the application of SMOTE. The results of the analysis show that public perception of the Free Lunch Program is mostly positive.
| Item Type: | Thesis (S1) |
|---|---|
| NIM/NIDN Creators: | 41520120011 |
| Uncontrolled Keywords: | Analisis sentimen, Naïve Bayes, Support Vector Machine, SMOTE, Program Makan Siang Gratis. Sentiment analysis, Naïve Bayes, Support Vector Machine, SMOTE, Free Lunch Program. |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | OKTAFIYANI AZ ZAHRO |
| Date Deposited: | 04 Feb 2025 07:59 |
| Last Modified: | 04 Feb 2025 07:59 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/93802 |
Actions (login required)
 |
View Item |
