Aqshal Win Mahara, . (2024) ANALISIS SENTIMEN APLIKASI SAYURBOX BERDASARKAN ULASAN DI GOOGLE PLAYSTORE MENGGUNAKAN NAÏVE BAYES CLASSIFIER. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (141kB) |
|
Text
AWAL.pdf Download (864kB) |
|
Text
BAB I.pdf Download (152kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (239kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (247kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (988kB) |
|
Text
BAB V.pdf Download (141kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (208kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (84kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (77kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (79kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (762kB) |
Abstract
Electronic commerce, or e-commerce, is the activity of buying or selling via the internet which includes buying, selling goods, services and information online. The growth of e-commerce is fueled by advances in technology and the internet, which has given rise to various e-commerce companies, including Sayurbox, an ecommerce platform that focuses on fruit and vegetables, facing challenges in maintaining its declining ranking in a competitive market. Evaluation was carried out through user sentiment analysis using the Naïve Bayes Classifier method on reviews on the Google Play Store. Data was collected from June 2024 using scraping using Python and taking data from 1000 reviews with public data type. The data goes through scraping stages of 1000 data then preprocessing stages (Cleaning, Case Folding, Tokenizing, Normalization, Stopword Removal, Stemming), word weighting using TF-IDF, and data division. Naïve Bayes produces 86% accuracy, 94.4% precision, 85% recall, 89.4% F1-Score with a training and test data ratio of 80:20. Apart from the classification results, there are wordcloud visualization results along with a graph of the frequency of the most words which are used to identify positive and negative sentiments. After doing the visualization, there was a positive value for the item with a weight of 370 and for the word send there was a negative result with a weight of 125. Another outcome was the creation of a simple website UI design using Figma to visualize the results.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil : 2010512118] [Pembimbing : Ati Zaidiah] [Penguji 1 : Theresia Wati] [Penguji 2 : Nur Hafifah Matondang] |
| Uncontrolled Keywords: | Sentiment Analysis, Google Play Store, Naïve Bayes Classifier, Sayurbox |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | AQSHAL WIN MAHARA |
| Date Deposited: | 22 Aug 2024 07:21 |
| Last Modified: | 22 Aug 2024 07:21 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31125 |
Actions (login required)
 |
View Item |