Fernaldi Anggadha, . (2025) ANALISIS SENTIMEN ULASAN APLIKASI LETTERBOXD DI GOOGLE PLAY MENGGUNAKAN METODE NAÏVE BAYES DAN INFORMATION GAIN. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (404kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (738kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (787kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (5MB) |
|
Text
BAB V.pdf Download (352kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (397kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (278kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (335kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (10MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (5MB) |
Abstract
This research aims to analyze user sentiment from reviews of the Letterboxd application on the Google Play Store using the Naïve Bayes classification method and Information Gain feature selection. In the digital era, user reviews serve as a critical indicator for evaluating application quality and performance. Naïve Bayes was chosen for its efficiency in text classification, while Information Gain was applied to filter the most relevant features to enhance model performance. A quantitative approach was employed, with review data collected via the google-play-scraper API between January and May 2025. Text preprocessing steps included case folding, cleaning, tokenization, stopword removal, and lemmatization. The data was then split using an 80:20 ratio for training and testing. Evaluation results showed that the Naïve Bayes model achieved 82.5% accuracy with precision and recall scores of 83% and 84%, respectively, meanwhile, combined with Information Gain, Naïve Bayes achieved an accuracy of 83.5%, with a precision of 84% and a recall of 85%.. Furthermore, a follow-up analysis was conducted by mapping negative sentiment results into seven software quality characteristics based on the ISO/IEC 25010 standard using a rule-based classification approach. These findings are expected to assist Letterboxd developers in enhancing application quality based on user sentiment and experience.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1810511069] [Pembimbing: Widya Cholil] [Penguji 1: Jayanta] [Penguji 2: Nurul Afifah Arifuddin] |
| Uncontrolled Keywords: | sentiment analysis, Naïve Bayes, Information Gain, ISO 25010, Google Play, Letterboxd. |
| 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: | FERNALDI ANGGADHA |
| Date Deposited: | 06 Aug 2025 01:07 |
| Last Modified: | 06 Aug 2025 01:07 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37670 |
Actions (login required)
 |
View Item |