Andhika Rizq Pulubuhu, . (2024) ANALISIS SENTIMEN PENGGUNA ANDROID TERHADAP APLIKASI INDOMARET POINKU MENGGUNAKAN METODE MAXIMUM ENTROPY. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (242kB) |
|
Text
AWAL.pdf Download (943kB) |
|
Text
BAB I.pdf Download (267kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (638kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (469kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB V.pdf Download (257kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (269kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (146kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (3MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
This research discusses sentiment analysis of Indomaret Poinku application users on the Android platform with the aim of providing insights into satisfaction, issues, and areas for improvement for developers. Data was collected from 6,435 user reviews on the Google Play Store. The results of the analysis will be used to create a data visualization dashboard for developers. Findings show variations in the number of reviews and star ratings, with the highest peak occurring in February and March due to Indomaret campaigns. Although the majority of reviews are positive, there is a significant number of negative reviews related to technical issues and application usage. The review classification process used TF-Idf word weighting and K-Fold Cross Validation, where classification without TF-Idf yielded better results with an average accuracy of 91.6%, a precision of 0.923, a recall of 0.949, and an F1-Score of 0.936. Text association analysis indicates that positive reviews reflect the application's strengths, while negative reviews highlight usage problems. Recommendations for improving application quality include optimizing the membership program, enhancing customer service, technical improvements, and implementing user suggestion features based on positive reviews, as well as improving performance, verification processes, and update management based on negative reviews.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512061] [Pembimbing 1: Bambang Saras Yulistiawan] [Pembimbing 2: Bambang Triwahyono] [Penguji 1: Ermatita] [Penguji 2: Iin Ernawati] |
| Uncontrolled Keywords: | Sentiment Analysis, Classification, K-Cross Validation, TF-IDF, Maximum Entropy |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | ANDHIKA RIZQ PULUBUHU |
| Date Deposited: | 04 Sep 2024 02:00 |
| Last Modified: | 04 Sep 2024 02:00 |
| URI: | http://repository.upnvj.ac.id/id/eprint/30865 |
Actions (login required)
 |
View Item |