Muhammad Nabil Nufail Pribadi, . (2024) PERBANDINGAN HASIL PENERAPAN ALGORITMA KLASIFIKASI DAN NATURAL LANGUAGE PROCESSING TERHADAP DATA KEPUASAN PENGGUNA LAYANAN TRANSPORTASI UMUM MRT JAKARTA. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (76kB) |
|
Text
AWAL.pdf Download (723kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (21kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (214kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (226kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (149kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (146kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (30kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (3MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (361kB) |
Abstract
Along with the increasing population and limited amount of land for housing in DKI Jakarta, it is no longer possible for each person to privately own a car-based transportation. This can be proven by the occurrences of traffic jams in DKI Jakarta with the biggest cause coming from the usage of private transportation, namely cars. MRT Jakarta is one of the solutions proposed by the government of DKI Jakarta as one of their efforts to overcome traffic jams. However, Jakarta's congestion level increases again in 2023 due to the increased usage of private transportation. Therefore, the author decided to classify the opinion of users of MRT Jakarta to find out the reasons why people choose or are reluctant to utilize MRT Jakarta as their main method of transportation, obtained from the social media X, utilizing natural language processing and machine learning algorithm such as Support Vector Machine, Random Forest Classifier, and multinomial Logistic Regression. The data amounts to 525 posts, with 222 in the 'positive' category, 185 in the 'negative' category, and 118 in the 'neutral' category. By dividing the dataset based on a comparison of 80% training data and 20% test data, the classification model with the highest accuracy score in this research, namely the model with the Random Forest Classifier algorithm, using the best parameters obtained through the usage of hyperparameter tuning technique, with the value of class_weight='balanced', value max_depth=350, min_samples_split=5, and n_estimators=200, resulting in an accuracy value of 81%, a precision value of 82.3%, a recall value of 81%, and an f1-score value of 81.5%, and successfully predicted 4 of 4 new data samples based on their target classes.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1910511106] [Pembimbing: Iin Ernawati] [Penguji 1: Widya Cholil] [Penguji 2: I Wayan Widi Pradnyana] |
| Uncontrolled Keywords: | Natural Language Processing, Classification, MRT Jakarta |
| 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: | MUHAMMAD NABIL NUFAIL PRIBADI |
| Date Deposited: | 04 Sep 2024 06:55 |
| Last Modified: | 04 Sep 2024 06:55 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31625 |
Actions (login required)
 |
View Item |