ANALISIS SENTIMEN ULASAN CASH ON DELIVERY DI SHOPEE MENGGUNAKAN METODE NAIVE BAYES

Mhartian Jordan Hutasoit, . (2024) ANALISIS SENTIMEN ULASAN CASH ON DELIVERY DI SHOPEE MENGGUNAKAN METODE NAIVE BAYES. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (227kB)
[img] Text
AWAL.pdf
Download (504kB)
[img] Text
BAB I.pdf
Restricted to Repository UPNVJ Only
Download (192kB)
[img] Text
BAB II.pdf
Restricted to Repository UPNVJ Only
Download (348kB)
[img] Text
BAB III.pdf
Restricted to Repository UPNVJ Only
Download (348kB)
[img] Text
BAB IV.pdf
Restricted to Repository UPNVJ Only
Download (511kB)
[img] Text
BAB V.pdf
Download (182kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (187kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (135kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (658kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (1MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (501kB)

Abstract

The author conducted research to analyze the sentiment of Cash On Delivery (COD) reviews on Shopee using the Naive Bayes algorithm. This method was chosen due to its effectiveness in handling text classification problems. The research utilized data from the Google Play Store collected through scraping techniques. These reviews were categorized into two sentiment categories: positive and negative. The analysis process began with data collection, followed by text preprocessing stages including case folding, tokenization, normalization, stopword removal, and stemming. The next stage involved splitting the data into 80% training data and 20% test data. The training data underwent TF-IDF (Term Frequency-Inverse Document Frequency) weighting, and the test data was evaluated using the Naive Bayes classification algorithm. The research results showed that the model utilizing the Naive Bayes algorithm achieved an accuracy rate of 66%, with the highest precision in the positive sentiment category at 67%, a recall of 30%, and an F-1 score of 41%. The model also demonstrated good performance in identifying negative reviews with a precision rate of 66%, a recall of 90%, and an F-1 score of 76%. This research provides insights into customer perceptions of their COD services. By leveraging the results of this sentiment analysis, Shopee can make improvements and adjustments to enhance customer satisfaction. This study also demonstrates that the Naive Bayes algorithm is an effective and efficient tool for sentiment analysis in e-commerce.

Item Type: Thesis (Skripsi)
Uncontrolled Keywords: Cash On Delivery, Sentiment Analysis, Naïve Bayes, Google Play Store, Shopee, TF-IDF, E-commerce
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: MHARTIAN JORDAN HUTASOIT
Date Deposited: 04 Oct 2024 06:20
Last Modified: 04 Oct 2024 06:20
URI: http://repository.upnvj.ac.id/id/eprint/31907

Actions (login required)

View Item View Item