Alessandro Samuel Tamada, . (2024) KLASIFIKASI SENTIMEN DATA TIDAK SEIMBANG MENGGUNAKAN ALGORITMA SMOTE & K-NEAREST NEIGHBOR PADA ULASAN PENGGUNA APLIKASI MAXIM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (14kB) |
|
Text
AWAL.pdf Download (569kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (60kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (223kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (256kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (759kB) |
|
Text
BAB 5.pdf Download (26kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (147kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (10kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (215kB) |
|
Text
HASIL PLAGIARISM.pdf Restricted to Repository staff only Download (6MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (416kB) |
Abstract
Maxim is an online motorbike taxi application that is used by many Indonesian people, as a newcomer but able to compete with other online motorbike taxis that were earlier, by providing lots of discounts and cheaper prices, at first there was a lot of controversy regarding this application because the service was not good, however From this research it was found that there were more good assessments than bad. This research takes data from reviews of the Maxim application and processes it so that it can be classified using the KNN algorithm. However, from the data obtained there is also quite a large difference between data labeled as negative and data labeled as positive, therefore you have to use the SMOTE algorithm to get balanced data labels. The results of this study used unbalanced data with positive data of 842 and negative data of 158. The highest value was obtained at K = 2, namely accuracy of 0.875, precision of 0.877, f1-score of 0.932, specificity of 0.111, and sensitivity of 0.994. while the second research carried out oversampling using the SMOTE technique so that the data could be balanced, then positive data became 842 and negative data also 842, the highest results were obtained at values K = 1 and 2 with the same values, namely accuracy 0.985, precision 1, f1-score 0.986, specificity 1 and sensitivity 0.973. Research with data that has gone through the SMOTE process has obtained very good results which can be seen from the specificity and sensitivity values which have a slight difference, indicating that the research data used is balanced. So it can be concluded that good data for research is balanced data.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1810511070] [Pembimbing 1: Ermatita] [Pembimbing 2: Neny Rosmawarni] [Penguji 1: . Widya Cholil] Penguji 2: Nindy Irzavika] |
| Uncontrolled Keywords: | Maxim, KNN, SMOTE. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | ALESSANDRO SAMUEL TAMADA |
| Date Deposited: | 02 Oct 2024 07:17 |
| Last Modified: | 02 Oct 2024 07:47 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31844 |
Actions (login required)
 |
View Item |