ANGGRAENI, PUSPITA SARI (2024) ANALISA SENTIMEN ULASAN PENGGUNA APLIKASI MERDEKA MENGAJAR DI GOOGLE PLAYSTORE MENGGUNAKAN ALGORITMA NAIVE BAYES. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (366kB) | Preview |
|
|
Text (ABSTRAK)
Abstrak.pdf Download (32kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab 1.pdf Restricted to Registered users only Download (41kB) |
|
|
Text (BAB II)
Bab 2.pdf Restricted to Registered users only Download (247kB) |
|
|
Text (BAB III)
Bab 3.pdf Restricted to Registered users only Download (78kB) |
|
|
Text (BAB IV)
Bab 4.pdf Restricted to Registered users only Download (552kB) |
|
|
Text (BAB V)
Bab 5.pdf Restricted to Registered users only Download (108kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pustaka.pdf Restricted to Registered users only Download (167kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (550kB) |
Abstract
Education has a big role in determining the quality of human resources. The role of teachers is very important as educators who provide guidance and learning. In an effort to make it easier for teachers to carry out their duties and responsibilities, especially in the independent curriculum, the Ministry of Education and Culture developed an application called Merdeka Mengajar. However, there is no method for classifying sentiment or opinion from comment data in the user satisfaction survey of the Merdeka Teaching application on Google Playstore, in order to find out the extent of user satisfaction with the Merdeka Teaching application. This study aims to observe the classification modeling of user opinions on free teaching applications on Google Playstore using the Random Forest & Naïve Bayes algorithm with TF-IDF text weighting, and to measure the performance of the two TF-IDF text weighting algorithms in the classification process. This study uses secondary data originating from user reviews of the independent teaching application, which is classified using the Random Forest & Naïve Bayes method using TF-IDF weighting. The results of this classification show that the Naïve Bayes algorithm in the independent teaching application displays a level of precision of 94%, accuracy of 95%, f1-score of 94% & recall, 94%, using testing data of 200 or 20% of 1837 data, through the total data The data observation technique used when testing. And the conclusion is that the Naïve Bayes algorithm has the lowest performance than the Random Forest algorithm. The Random Forest algorithm with 80-90% data train has the greatest accuracy performance than the Naïve Bayes algorithm. So there is a need for a more in-depth analysis to ensure user satisfaction in implementing the independent teaching application. Keywords : Sentiment Analysis, Naive Bayes, Random Forest, Merdeka Mengajar Pendidikan mempunyai peran besar dalam menentukan kualitas sumber daya manusia. Peranan guru amatlah penting sebagai pendidik yang memberikan bimbingan dan pembelajaran. Sebagai upaya dalam memudahkan para guru untuk melakukan tugas dan tanggung jawabnya terutama pada kurikulum merdeka, Kemendikbud mengembangkan aplikasi bernama Merdeka Mengajar. Namun belum adanya metode untuk mengklasifikasikan sentiment atau opini dari data komentar pada survei kepuasan pengguna aplikasi tersebut di google playstore, guna mengetahui sejauh mana kepuasan pengguna terhadap aplikasi merdeka mengajar. Pengkajian ini bertujuan untuk mengamati pemodelan klasifikasi opini pemakai aplikasi merdeka mengajar di google playstore serta untuk mengukur kinerja dari pengimplementasian algoritma Random Forest & Naïve Bayes secara pembobotan teks TF-IDF. Pengkajian ini memakai data sekunder yang berasal melalui ulasan pengguna aplikasi merdeka mengajar, yang diklasifikasi dengan metode Random Forest & Naïve Bayes memakai pembobotan TF-IDF. Hasil dari pengklasifikasian tersebut menunjukkan bahwa, algoritma Naïve Bayes pada apliksi merdeka mengajar menampilkan taraf presisi 94%, akurasi 95%, f1-score 94% & recall, 94%, memakai data testing sejumlah 200 atau 20% dari 1837 data, melalui total data yang dipakai secara tehnik observasi data ketika testing. Dan dengan kesimpulan algoritma Naïve Bayes mempunyai performance terminim daripada algoritma Random Forest. Algoritma Random Forest dengan data train 80- 90% mempunyai performance akurasi terbesar daripada algoritma Naïve Bayes. Maka perlu adanya Analisa yang lebih mendalam untuk memastikan kepuasan pengguna dalam implementasi aplikasi merdeka mengajar. Kata Kunci : Analisa Sentimen, Naive Bayes, Random Forest, Merdeka Mengajar
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/SI. 24 103 |
| NIM/NIDN Creators: | 41820010088 |
| Uncontrolled Keywords: | Analisa Sentimen, Naive Bayes, Random Forest, Merdeka Mengajar |
| Subjects: | 300 Social Science/Ilmu-ilmu Sosial > 370 Education/Pendidikan > 371 Educational Institutions, Schools and Their Activities/Institusi Pendidikan, Sekolah dan Aktifitasnya > 371.3 Methods of Instruction and Study/Metode Belajar Mengajar, Kegiatan Belajar Mengajar 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma 700 Arts/Seni, Seni Rupa, Kesenian > 710 Civic and Lanscape Art/Seni Perkotaan dan Pertamanan > 719 Natural Landscapes/Pertamanan Alam |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | khalimah |
| Date Deposited: | 26 Jul 2024 03:50 |
| Last Modified: | 26 Jul 2024 03:50 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/89839 |
Actions (login required)
 |
View Item |
