VISUALISASI DATA ANALISIS SENTIMEN TERHADAP APLIKASI E-COMMERCE ZALORA BERDASARKAN ULASAN DI GOOGLE PLAY STORE MENGGUNAKAN METODE NAIVE BAYES CLASSIFIER

Raditya Rafi Harimasya, . (2024) VISUALISASI DATA ANALISIS SENTIMEN TERHADAP APLIKASI E-COMMERCE ZALORA BERDASARKAN ULASAN DI GOOGLE PLAY STORE MENGGUNAKAN METODE NAIVE BAYES CLASSIFIER. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (15kB)
[img] Text
AWAL.pdf
Download (1MB)
[img] Text
BAB I.pdf
Download (271kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (176kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (4MB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (5MB)
[img] Text
BAB V.pdf
Download (71kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (203kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (88kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (4MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (6MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (4MB)

Abstract

Electronic commerce, or e-commerce, is the activity of buying and selling goods and services over the internet, encompassing online purchases, sales, services, and information. The growth of e-commerce is driven by technological advancements and the internet, leading to the emergence of various e-commerce companies, including ZALORA, an e-commerce platform focusing on fashion, which faces challenges in maintaining its declining ranking in the competitive market. Evaluation is conducted through user sentiment analysis using the Naïve Bayes Classifier method on reviews from the Google Play Store. Data were collected from December 2022 to October 2023 and underwent preprocessing, word weighting using TF-IDF, and data splitting. Naïve Bayes achieved an accuracy of 86%, precision of 95%, recall of 88%, and F1-Score of 91% with an 70:20 ratio of training and testing data. In addition to classification results, there are visualization outputs such as word clouds and graphs depicting the frequency of most-used words for identifying positive and negative sentiments. Another output is the development of a simple website system using the Streamlit Framework for visualization purposes.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2010512112] [Pembimbing 1: Ati Zaidiah] [Pembimbing 2: Nindy Irzavika] [Penguji 1: Bambang Saras Yulistiawan] [Penguji 2: Iin Ernawati]
Uncontrolled Keywords: Sentiment Analysis, Google Play Store, Naïve Bayes classifier, Zalora
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: RADITYA RAFI HARIMASYA
Date Deposited: 04 Sep 2024 01:53
Last Modified: 04 Sep 2024 01:53
URI: http://repository.upnvj.ac.id/id/eprint/30559

Actions (login required)

View Item View Item