PERBANDINGAN ALGORITMA SUPERVISED LEARNING PADA ANALISIS SENTIMEN PENGGUNA TOKOPEDIA DI GOOGLE PLAY

YULIANTI, AIDA (2023) PERBANDINGAN ALGORITMA SUPERVISED LEARNING PADA ANALISIS SENTIMEN PENGGUNA TOKOPEDIA DI GOOGLE PLAY. S1 thesis, Universitas Mercu Buana Bekasi.

[img]
Preview
Text
41519310039 - AIDA YULIANTI - 01 COVER.pdf

Download (240kB) | Preview
[img]
Preview
Text
41519310039 - AIDA YULIANTI - 02 ABSTRAK.pdf

Download (35kB) | Preview
[img] Text
41519310039 - AIDA YULIANTI - 03 BAB 1.pdf
Restricted to Registered users only

Download (113kB)
[img] Text
41519310039 - AIDA YULIANTI - 04 BAB 2.pdf
Restricted to Registered users only

Download (137kB)
[img] Text
41519310039 - AIDA YULIANTI - 05 BAB 3.pdf
Restricted to Registered users only

Download (111kB)
[img] Text
41519310039 - AIDA YULIANTI - 06 BAB 4.pdf
Restricted to Registered users only

Download (162kB)
[img] Text
41519310039 - AIDA YULIANTI - 07 BAB 5.pdf
Restricted to Registered users only

Download (280kB)
[img] Text
41519310039 - AIDA YULIANTI - 08 DAFTAR PUSTAKA.pdf
Restricted to Registered users only

Download (931kB)
[img] Text
41519310039 - AIDA YULIANTI - 09 LAMPIRAN.pdf
Restricted to Registered users only

Download (1MB)

Abstract

Supervised learning merupakan jenis pembelajaran mesin yang memanfaatkan data yang telah dilabeli sebelumnya untuk menghasilkan model prediksi yang lebih akurat terhadap data yang belum pernah dilihat sebelumnya. Hal ini menjadikan algoritma supervised learning banyak digunakan sebagai metode penyelesaian berbagai persoalan, seperti klasifikasi. Maka dari itu penelitian ini menggunakan metode klasifikasi yang dilakukan pada analisis sentimen dengan menerapkan algoritma Naïve Bayes, Support Vector Machine (SVM) dan K-Nearst Neighbors (KNN). Selanjutnya algortma tersebut akan dibandingkan untuk mendapkan hasil klasifikasi terbaik dalam analisis sentimen pada salah satu marketplace yaitu Tokopedia di google play. Sehingga nantinya para pengguna bisa mengetahui informasi yang terdapat di Tokopedia. Informasi yang ada dikategorikan menjadi 3 (tiga) kategori yaitu sentimen positive, sentimen negative, dan sentimen neutral. Kemudian data tersebut dievaluasi dengan uji matriks konfusi dimana akurasi, presisi, dan recall sebagai parameternya. Berdasarkan pengujian menghasilkan nilai akurasi algoritma SVM memperoleh akurasi mencapai 90% dengan presisi dan recall 89% dan 90%. Selanjutnya Niave Bayes dengan akurasi mencapai 89%, presisi 85%, dan recall 89%. Dan yang terakhir KNN dengan akurasi mencapai 81%, presisi 78%, dan recall 81%. Sehingga dapat di Tarik kesimpulan bahwa dengan algoritma SVM memberikan hasil yang paling akurat saat menganalisis pendapat pengguna Tokopedia di Google Play dibandingkan kedua algoritma lainnyaa. Kata Kunci: pre-processing, marketplace, analisis sentimen, SVM, Naïve Bayes, KNN Supervised learning is a type of machine learning that utilizes previously labeled data to produce more accurate predictive models for data that has never been seen before. This makes supervised learning algorithms widely used to solve various problems, such as classification. In this study the classification was carried out on sentiment analysis using the Naïve Bayes algorithm, Support Vector Machine (SVM) and K-Nearst Neighbors (KNN). Then the algorithm will be compared to get the best classification results in sentiment analysis on one of the marketplaces, namely Tokopedia on Google Play. So that later users can find out the information contained in Tokopedia. The information is divided into 3 categories, namely positive sentiment, negative sentiment, and neutral sentiment. The data is then evaluated using the confusion matrix test with parameters of accuracy, precision, and recall. Based on the test, it shows that the accuracy value of the SVM algorithm obtains an accuracy of up to 90% with a precision and recall of 89% and 90%. Next is Naïve Bayes with 89% accuracy, 85% precision and 89% recall. And finally KNN with accuracy reaching 81%, precision 78%, and recall 81%. So it can be concluded that the Support Vector Machine (SVM) algorithm provides the most accurate results when analyzing the opinions of Tokopedia users on Google Play compared to the other two algorithms. Keywords: sentiment analysis, pre-processing, marketplace, Naïve Bayes, SVM, KNN

Item Type: Thesis (S1)
Call Number CD: FIK/INFO 23 045
NIM/NIDN Creators: 41519310039
Uncontrolled Keywords: pre-processing, marketplace, analisis sentimen, SVM, Naïve Bayes, KNN
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 > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: siti maisyaroh
Date Deposited: 29 Sep 2023 04:12
Last Modified: 29 Sep 2023 04:12
URI: http://repository.mercubuana.ac.id/id/eprint/81630

Actions (login required)

View Item View Item