ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI PADA GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE

SANNY KHAIRANI LUBIS, NPM 2007100015 (2023) ANALISIS SENTIMEN ULASAN PENGGUNA APLIKASI PADA GOOGLE PLAY STORE MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE. Tugas_Akhir (Artikel) INFORMATIKA Universitas Labuhanbatu, 12 (3). pp. 120-128. ISSN 2615-1855 (e-ISSN)/ 2303-2863 (p-ISSN)

[img] Text
COVER FULL.pdf
Download (1MB)
[img] Text
ARTIKEL.pdf
Download (463kB)

Abstract

One of the most popular e-commerce sites in Indonesia is Shopee. As the largest marketplace application in Indonesia, Shopee provides product and service review features to users on the Google Play Store. The review feature is very helpful to find out whether user reviews are positive or negative. Having user reviews will help Shopee improve its services. To identify a very large number of user reviews, it is not possible to do it manually by reading them one by one. This process will take a very long time and is not effective. Therefore, we need a method that is able to identify reviews from users more effectively and efficiently. This research aims to conduct sentiment analysis of user reviews of the Shopee application on the Google Play Store by applying the Support Vector Machine algorithm. The research stages carried out started with dataset collection, dataset labeling, preprocessing, TF-IDF weighting, classification, and evaluation. From the research results, accuracy was 70.88%, precision was 49.49%, recall was 52.55%, and F1-score was 49.84%. From these results, it can be concluded that the performance of the support vector machine algorithm in classifying the sentiment of user reviews of the Shopee application on the Google Play Store is quite good. Keywords : E-commerce, Classification, Sentiment Analysis, Shopee, SVM, TF-IDF.

Item Type: Article
Uncontrolled Keywords: E-commerce, Classification, Sentiment Analysis, Shopee, SVM, TF-IDF.
Subjects: T Technology > T Technology (General)
Z Bibliography. Library Science. Information Resources > ZA Information resources
Divisions: Fakultas Sains Dan Teknologi > Informatika Komputer
Depositing User: Unnamed user with email repository@ulb.ac.id
Date Deposited: 04 Sep 2024 02:19
Last Modified: 04 Sep 2024 02:19
URI: http://repository.ulb.ac.id/id/eprint/1015

Actions (login required)

View Item View Item
ulb is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.