SHELVIYANAH, SHELVIYANAH (2022) VARIOUS EXPERIMENTS OF NAVE BAYES AND DECISION TREE ON E-COMMERCE APPLICATION REVIEWS. S1 thesis, Universitas Mercu Buana.
|
Text (HAL COVER)
01 Cover.pdf Download (1MB) | Preview |
|
|
Text (ABSTRAK)
02 Abstrak.pdf Download (24kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB 1)
03 Bab 1.pdf Restricted to Registered users only Download (124kB) |
|
|
Text (BAB 2)
04 Bab 2.pdf Restricted to Registered users only Download (136kB) |
|
|
Text (BAB 3)
05 Bab 3.pdf Restricted to Registered users only Download (328kB) |
|
|
Text (BAB 4)
06 Bab 4.pdf Restricted to Registered users only Download (318kB) |
|
|
Text (BAB 5)
07 Bab 5.pdf Restricted to Registered users only Download (539kB) |
|
|
Text (BAB 6)
08 Bab 6.pdf Restricted to Registered users only Download (18kB) |
|
|
Text (DAFTAR PUSTAKA)
09 Daftar Pustaka.pdf Restricted to Registered users only Download (88kB) |
|
|
Text (LAMPIRAN)
10 Lampiran.pdf Restricted to Registered users only Download (192kB) |
Abstract
Currently, there are many kinds of applications that offer e-commerce services, examples of e-commerce applications are Tokopedia and JD.ID. Many users who use the application and provide reviews of the application are challenging to analyze. This research is focused on text classification of user reviews of the Tokopedia and JD.ID applications by comparing the performance of the Naïve Bayes and Decision Tree methods and measuring the effect of various experiments to find the method that has the best assessment results and performance with correct predictions in classifying positive or negative reviews. In conclusion, the tuning parameters, the use of N-gram, and the selection of Chi-Square features have an effect on several cases in the performance of the two models. The results showed that the Decision Tree model with a proportion of 80:20 was superior to the Naïve Bayes model with an accuracy of 93.50% while the Naïve Bayes model only had an accuracy of 91%. Key words: Sentiment analysis, text classification, e-commerce, n-gram, feature selection Saat ini banyak sekali jenis aplikasi yang menawarkan layanan e-commerce, contoh aplikasi e-commerce adalah Tokopedia dan JD.ID. Banyak pengguna yang menggunakan aplikasi dan memberikan ulasan tentang aplikasi tersebut sulit untuk dianalisis. Penelitian ini difokuskan pada klasifikasi teks review pengguna aplikasi Tokopedia dan JD.ID dengan membandingkan kinerja metode Naïve Bayes dan Decision Tree serta mengukur pengaruh berbagai eksperimen untuk menemukan metode yang memiliki hasil penilaian dan kinerja terbaik dengan prediksi yang benar dalam mengklasifikasikan ulasan positif atau negatif. Kesimpulannya, parameter tuning, penggunaan N-gram, dan pemilihan fitur Chi-Square berpengaruh pada beberapa kasus dalam kinerja kedua model. Hasil penelitian menunjukkan bahwa model Decision Tree dengan proporsi 80:20 lebih unggul dari model Naïve Bayes dengan akurasi 93,50% sedangkan model Naïve Bayes hanya dapat akurasi sebesar 91%. Kata kunci: Sentimen analisis, klasifikasi teks, e-commerce, n-gram, seleksi fitur
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/INFO. 22 060 |
| NIM/NIDN Creators: | 41517010008 |
| Uncontrolled Keywords: | Sentimen analisis, klasifikasi teks, e-commerce, n-gram, seleksi fitur |
| Subjects: | 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika |
| Divisions: | Fakultas Ilmu Komputer > Informatika |
| Depositing User: | LUTHFIAH RAISYA ARDANI |
| Date Deposited: | 15 Sep 2022 08:51 |
| Last Modified: | 19 Sep 2022 03:24 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/69132 |
Actions (login required)
 |
View Item |
