THORIQ, AHMAD NAJMI (2025) PENERAPAN ALGORITMA MACHINE LEARNING UNTUK ANALISIS PREDIKSI MASYARAKAT TERHADAP PILKADA JAKARTA 2024. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (565kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (34kB) |
|
|
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (69kB) |
|
|
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (35kB) |
|
|
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 (28kB) |
|
|
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (89kB) |
|
|
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (735kB) |
Abstract
The 2024 Jakarta gubernatorial election is widely discussed both in the real world and online, especially on social media Twitter. Social media, especially Twitter, has now become a great place to comment and express opinions according to each person's opinion. This study is expected to contribute to public opinion research with positive, neutral, or negative comments. The methods used in this study mainly use data tokenization, cleaning, and word filtering to determine predictions using the Lexicon Based method. Naive Bayes Classifier (NBC) and Support Vector Machine (SVM) are used for classification. The data used were 6872 Indonesian language tweets containing the keywords "Public Opinion Pilkada", "Issu Pilkada Jakarta 2024", "Pilkada Jakarta 2024" and "Anies". The prediction of the 2024 Jakarta gubernatorial candidate is the result of this research. By using the support vector machine (SVM) classification method, the highest accuracy was obtained at 81%, a high rate of 84%, a return rate of 81%, a TP rate of 81% and a TN rate of 81.6%. Keywords : analisis prediction, jakarta governor candidate 2017, lexicon based, naïve bayes classifier, support vector machine. Pilkada DKI Jakarta 2024 ramai diperbincangkan baik di dunia nyata maupun online, terutama di media sosial Twitter. Media sosial khususnya Twitter kini telah menjadi tempat yang bagus dan berkomentar dan beropini sesuai dengan pendapat masing masing. Penelitian ini diharapkan dapat memberikan kontribusi pada penelitian opini publik dengan komentar positif, netral, atau negatif. Metode yang digunakan dalam penelitian ini terutama menggunakan tokenisasi data, pembersihan, dan pemfilteran kata untuk menentukan prediksi menggunakan metode Lexicon Based. Naive Bayes Classifier (NBC) dan Support Vector Machine (SVM) digunakan untuk klasifikasi. Data yang digunakan sebanyak 6872 data tweet berbahasa Indonesia yang memuat kata kunci “Opini Publik Pilkada”, “Isu Pilkada Jakarta 2024”, “Pilkada Jakarta 2024” dan “Anies”. Prediksi calon gubernur DKI Jakarta 2024 merupakan hasil penelitian tersebut. Dengan menggunakan metode klasifikasi support vector machine (SVM) diperoleh akurasi tertinggi sebesar 81%, high rate sebesar 84%, return rate sebesar 81%, TP rate sebesar 81% dan TN rate sebesar 81.6%. Kata kunci: analisis prediksi, calon gubernur dki jakarta 2024, lexicon based, naïve bayes classifier, support vector machine.
Actions (login required)
 |
View Item |
