Alfan, Afiyudin (2025) ANALISIS SENTIMEN DAN IDENTIFIKASI POLA KELUHAN PADA APLIKASI GOFOOD MERCHANT MENGGUNAKAN NAÏVE BAYES DAN APRIORI BERDASARKAN ULASAN PENGGUNA DI PLAY STORE. Undergraduate thesis, UPN VETERAN JATIM.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
21032010106-Cover.pdf Download (3MB) |
|
Text (Bab 1)
21032010106-Bab 1.pdf Download (269kB) |
|
Text (Bab 2)
21032010106-Bab 2.pdf Restricted to Repository staff only until 25 July 2027. Download (836kB) |
|
Text (Bab 3)
21032010106-Bab 3.pdf Restricted to Repository staff only until 25 July 2027. Download (326kB) |
|
Text (Bab 4)
21032010106-Bab 4.pdf Restricted to Repository staff only until 25 July 2027. Download (1MB) |
|
Text (Bab 5)
21032010106-Bab 5.pdf Download (326kB) |
|
Text (Daftar Pustaka)
21032010106-Daftar Pustaka.pdf Download (343kB) |
|
Text (Lampiran)
21032010106-Lampiran.pdf Restricted to Repository staff only Download (431kB) |
Abstract
Competition in Indonesia’s digital culinary service industry is becoming increasingly intense, in line with the growing adoption of technology and the use of digital business management platforms by entrepreneurs. One widely used platform is GoFood Merchant. Although relatively popular, GoFood Merchant still ranks below Grab Merchant in terms of download numbers, indicating a challenge in maintaining and improving its competitiveness. One effort to understand the factors affecting user satisfaction is by analyzing user reviews posted on the Google Play Store. This study aims to identify user sentiment toward the GoFood Merchant application and discover frequently occurring complaint patterns. The methods used are Naïve Bayes for sentiment analysis and the Apriori algorithm to find association rules from negative reviews. The data consists of 1,243 user reviews collected through web scraping from the Google Play Store. These reviews were labeled into two sentiment categories: positive and negative. The labeled negative reviews were then analyzed using the Apriori algorithm to identify dominant complaint patterns. The classification results show that positive reviews outnumber negative ones, with the Naïve Bayes model achieving an accuracy rate of 87%. The Apriori algorithm revealed associations such as the keywords “driver” and “order” being linked to “slow,” “search,” “cancel,” “system,” and “loss.” The keyword “application” was associated with “crash,” “service,” and “poor,” while “restaurant” was linked to “rating,” “system,” “drop,” and “disappointed.” The keyword “advertisement” was associated with “deduction,” “cost,” and “expensive.” These association patterns were then used as the basis for formulating improvement recommendations using the 5W+1H approach.
| Item Type: | Thesis (Undergraduate) | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||
| Subjects: | T Technology > T Technology (General) > T55.4-60.8 Industrial engineering. Management engineering | ||||||||
| Divisions: | Faculty of Engineering > Departement of Industrial Engineering | ||||||||
| Depositing User: | Alfan Afiyudin | ||||||||
| Date Deposited: | 25 Jul 2025 07:39 | ||||||||
| Last Modified: | 25 Jul 2025 07:39 | ||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/41033 |
Actions (login required)
 |
View Item |