Tantri Ayu Prasetiarini, . (2020) Analisis Sentimen Media Sosial Twitter Menggunakan Metode Support Vector Machine (SVM). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (12kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB 1.pdf Download (133kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (512kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (198kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (898kB) |
|
Text
BAB 5.pdf Download (122kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (124kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (57kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (232kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository UPNVJ Only Download (778kB) |
Abstract
Twitter social media is a place to exchange information. The information can be in the form of an opinion addressed by a particular company. These opinions can be analyzed into sentiment analysis which will help in understanding the sentiments of public opinion in the form of texts that were initially unstructured into structured. The opinion data is labeled and classified into positive classes, and negative classes, using the support vector machine (SVM) method, where the data used comes from the social media twitter @indonesiagaruda. From the results of the classification method using the Support Vector Machine (SVM) an evaluation of the model is done using a confusion matrix against calculations, so that the accuracy value of 88.75% is obtained by using a linear kernel, while the polynomial kernel gets an accuracy value of 75.625%. The highest accuracy model is used for predicting new data using 564 tweets in February 2020, to analyze sentiment in the form of visualization based on the level of satisfaction with services based on facilities, timeliness, assessment of ticket rates, assessment of customer service, and rating against GarudaMiles and the Garuda Indonesia website. From the results of the prediction model, there are 291 positive sentiments and 273 negative sentiments, with a high positive sentiment rating in the category of facilities, timeliness, customer service, while high negative sentiment ratings in the ticket fare category, GarudaMiles and Garuda Indonesia website in February 2020.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No. Panggil : 1610511018] [Pembimbing 1 : Iin Ernawati] [Pembimbing 2 : Nurul Chamidah] [Penguji 1 : Henki Bayu Seta] [Penguji 2 : I Wayan Widi[ |
| Uncontrolled Keywords: | twitter, support vector machine, sentiment analysis |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | Tantri Ayu Prasetiarini |
| Date Deposited: | 12 Jan 2022 04:49 |
| Last Modified: | 12 Jan 2022 04:49 |
| URI: | http://repository.upnvj.ac.id/id/eprint/6737 |
Actions (login required)
 |
View Item |