Muhammad Raziv Maulana Ranie, . (2024) ANALISIS SENTIMEN PENGGUNA CITYMAPPER BERDASARKAN ULASAN PADA APP STORE DAN GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (72kB) |
|
Text
AWAL.pdf Download (366kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (164kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (296kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (233kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB V.pdf Download (78kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (92kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (103kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
PLAGIARISME.pdf Restricted to Repository staff only Download (1MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (791kB) |
Abstract
Digital map apps have become an essential part of life, allowing users to plan trips, find the fastest routes, and get real-time transportation information. One such digital map app is Citymapper, which is designed to provide comprehensive guidance on public transportation, walking, or using private vehicles. Compared to similar apps, Citymapperoffers special features such as multi-modal travel time predictions, transportation disruption notifications, and detailed transit station guides. This research uses the Support Vector Machine method to analyze user sentiment towards the Citymapper app based on reviews in the App and Google Play Stores. The review data collected from September 2023 to March 2024 was then manually labeled by 3 annotators. The data will go through various stages before classification is carried out, such as the preprocessing stage, word weighting with the Term Frequency - Inverse Document Frequency (TF-IDF) method, and data division with a ratio of 80:20. This study aims to determine the sentiment, accuracy and visualization results of the SVM algorithm in classifying user review data. The results showed that the SVM classification model provided good performance. For reviews from the App Store, the model achieved 81% accuracy, 85% precision, 92% recall, and 89% f1-score. Meanwhile, for reviews from the Google Play Store, the accuracy was 87%, precision 81%, recall 93%, and f1-score 87%. In addition to the classification results, the research also created a data visualization in the form of a word cloud to identify key words that often appear in positive and negative reviews.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512093] [Pembimbing 1: Nurhafifah Matondang] [Pembimbing 2: Sarika] [Penguji 1: Zatin Niqotaini] [Penguji 2: Nindy Irzavika] |
| Uncontrolled Keywords: | Sentiment Analysis, Maps, Citymapper, Support Vector Machine (SVM). |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | MUHAMMAD RAZIV MAULANA RANIE |
| Date Deposited: | 04 Feb 2025 02:13 |
| Last Modified: | 20 Feb 2025 07:36 |
| URI: | http://repository.upnvj.ac.id/id/eprint/35794 |
Actions (login required)
 |
View Item |