ANALISIS SENTIMEN PADA REVIEW PENGGUNA E-COMMERCE BIDANG PANGAN MENGGUNAKAN METODE SUPPORT VECTOR MACHINE : (Studi Kasus: Review Sayurbox Dan Tanihub Pada Google Play)

Geyessella Manik, . (2021) ANALISIS SENTIMEN PADA REVIEW PENGGUNA E-COMMERCE BIDANG PANGAN MENGGUNAKAN METODE SUPPORT VECTOR MACHINE : (Studi Kasus: Review Sayurbox Dan Tanihub Pada Google Play). Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (15kB)
[img] Text
AWAL.pdf
Download (1MB)
[img] Text
BAB 1.pdf
Download (199kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (430kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (381kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 5.pdf
Download (131kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (143kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (27kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (748kB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (1MB)

Abstract

Sayurbox and Tanihub are digital startups that help people by selling agricultural products online. The image of public opinion in the form of positive and negative impressions is an important thing that a company usually wants to know because it can affect the attractiveness of the company and affect the effectiveness of marketing the company's products or services. Opinions from the public are loaded in large numbers, so we need a technique that can group those opinions automatically quickly. Techniques that can be used in businesses to determine public opinion, including positive or negative are text mining applications. One of the fields of text mining that is commonly used is sentiment analysis which is useful for obtaining information by monitoring user opinions on the products or services provided by the company. Sayurbox and Tanihub are two different e-commerce sites but provide services in the same field that can be accessed by downloading them from the Google Play site. In conducting the sentiment analysis process, raw data is obtained by withdrawing rating and review data from the Google Play site. Furthermore, the data is cleaned of words and symbols that are not relevant to the sentiment and then labeled it into two classes, namely positive and negative. Before entering the classification process, the review data which is still of qualitative value is converted into data of quantitative value by using the Term Frequency Inverse Document Frequency (TF IDF method). The results of the classification using the Support Vector Machine (SVM method) with a period of February 2020 to January 2021 obtained the highest accuracy is in the data review sayurbox of 91.4% with the highest number of sentiments being positive sentiment as much as 738 (70%). While in the data review tanihub, the total accuracy is 88.8% with the most positive sentiment, which is 348 (65%). The proportion of data sharing used is 80 : 20.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil : 1710511004] [Pembimbing : Iin Ernawati] [Penguji 1 : Yuni Widiastiwi] [Penguji 2 : Nurul Chamidah]
Uncontrolled Keywords: Sentiment Analysis, E-commerce, Sayurbox, Tanihub, Text Mining, SVM Classifier, Google Play.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Geyessella Manik
Date Deposited: 21 Dec 2021 07:19
Last Modified: 21 Dec 2021 07:19
URI: http://repository.upnvj.ac.id/id/eprint/11215

Actions (login required)

View Item View Item