Hansen Kallista, . (2024) ANALISIS SENTIMEN APLIKASI SOLOLEARN BERDASARKAN FEEDBACK PENGGUNA DI GOOGLE PLAY STORE UNTUK MENGEVALUASI WAWASAN PENGGUNA APLIKASI MENGGUNAKAN ALGORITMA NAÏVE BAYES. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (139kB) |
|
Text
AWAL.pdf Download (3MB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (179kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (297kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (791kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB V.pdf Download (166kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (172kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (336kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (15MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (3MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (792kB) |
Abstract
Sentiment analysis has evolved into one of the most active research fields in Natural Language Processing, and industrial activities around sentiment analysis of applications have also rapidly developed. Sololearn is an educational application developed by an American company that allows its users to learn programming languages such as HTML, CSS, JavaScript, etc., equipped with features like a code compiler. Therefore, the author wants to conduct research on the Sololearn application to observe user sentiment toward the application and to study its strengths and weaknesses. With a total of 728 review data obtained through data scraping from the Google Play Store, the data were then manually labeled using the review rating system where if the review had a rating of 4 and 5, the data was labeled positive, whereas if the review had a rating of 3 or lower, the data was labeled negative. The data went through a pre-processing stage to ensure the data was ready to be processed, then using the TF-IDF word weighting method. After all pre-process stages were completed, the data was used to implement the model using the naïve bayes algorithm with an 80% training data and 20% testing data split. The results obtained from this model creation were an accuracy score of 80%, a precision score of 64%, a recall of 80%, and an f1-score of 71%. The results of this sentiment analysis indicate that users expect the addition of an Indonesian language feature to facilitate the learning process, as well as the fixing of bugs still present in some of the courses offered.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512084] [Pembimbing 1: Rio Wirawan] [Pembimbing 2: Ruth Mariana Bunga Wadu] [Penguji 1: Ati Zaidiah] [Penguji 2: Iin Ernawati] |
| Uncontrolled Keywords: | Sentiment Analysis, Sololearn, Naïve Bayes, Data Modelling |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | HANSEN KALLISTA |
| Date Deposited: | 29 Aug 2024 07:44 |
| Last Modified: | 29 Aug 2024 07:44 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31924 |
Actions (login required)
 |
View Item |