Ikhlasul Amal, . (2023) IMPLEMENTASI ALGORITMA SUPPORT VECTOR MACHINE (SVM) UNTUK ANALISIS SENTIMEN TERHADAP KENAIKAN HARGA BBM PERTAMINA PADA MEDIA SOSIAL TWITTER. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (624kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB 1.pdf Download (774kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (977kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (983kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (691kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (629kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (497kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (1MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
On September 3, 2022, the government officially announced an increase in the price of diesel, Pertalite, and Pertamax fuels. Various responses and complaints from the community were shed, one of them via social media Twitter. Users as a community, there are lots of tweets on Twitter with the keyword or hashtag (#) bbm goes up, of course, there is a lot of data that must be accommodated, then from that required sentiment analysis to find out the sentiments of Twitter users towards Pertamina's fuel price increase on Twitter and find out the performance comparison of the Support Vector Machine (SVM) algorithm using data from automatic labeling and manual labeling. The data taken is tweet data using the twint python library assisted by the Docker application Desktop and VSCode. Then do preprocessing with stages of data cleaning, case folding, normalization, tokenization, stopword removal, and stemming. After that, the data is labeled positive and negative automatically using the Lexicon Based obtained by 2963 positive and 1114 negative, and manually by 2 the annotator by calculating the kappa statistic obtained 2838 positive and 1239 negative, then weighting words using Term Frequency – Inverse Document Frequency (TF-IDF). Then the data is divided into 80% training data and 20% random test data. The classification results of automatic and manual labeling data using the Support Vector Machine (SVM) algorithm each have accuracy values of 83% and 81%, precision of 86% and 84%, recall of 92% and 91%, specificity of 58% and 56%, and F1-score of 89% and 88%.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil: 1910511125] [Pembimbing: Jayanta] [Penguji 1: Yuni Widiastiwi] [Penguji 2: Rio Wirawan] |
| Uncontrolled Keywords: | Fuel Price Increase, Twitter, Sentiment Analysis, Classification, Support Vector Machine (SVM) |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Ikhlasul Amal |
| Date Deposited: | 14 Aug 2023 03:11 |
| Last Modified: | 14 Aug 2023 03:11 |
| URI: | http://repository.upnvj.ac.id/id/eprint/25247 |
Actions (login required)
 |
View Item |