PENERAPAN ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE UNTUK ANALISIS SENTIMEN TERHADAP E-COMMERCE INDONESIA

PUSPITA, ANGELA INDAH (2022) PENERAPAN ALGORITMA NAÏVE BAYES DAN SUPPORT VECTOR MACHINE UNTUK ANALISIS SENTIMEN TERHADAP E-COMMERCE INDONESIA. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 Cover.pdf Download (225kB) | Preview
Preview	Text (ABSTRAK) 02 Abstrak.pdf Download (27kB) | Preview
	Text (BAB I) 03 Bab 1.pdf Restricted to Registered users only Download (30kB)
	Text (BAB II) 04 Bab 2.pdf Restricted to Registered users only Download (79kB)
	Text (BAB III) 05 Bab 3.pdf Restricted to Registered users only Download (95kB)
	Text (BAB IV) 06 Bab 4.pdf Restricted to Registered users only Download (113kB)
	Text (BAB V) 07 Bab 5.pdf Restricted to Registered users only Download (22kB)
	Text (DAFTAR PUSTAKA) 08 Daftar Pustaka.pdf Restricted to Registered users only Download (33kB)
	Text (LAMPIRAN) 09 Lampiran.pdf Restricted to Registered users only Download (1MB)

Abstract

Existence of Covid-19 pandemic which is endemic in all countries including Indonesia, has caused the government to make policies namely Pembatasan Sosial Berskala Besar (PSBB) in many fields, one of which is the economy. This policy gave rise to a new trend in society, namely online shopping habit. The trend of buying online through e-commerce is increasingly in demand, because e-commerce doesn’t hesitate to provide substantial discounts and free shipping. However, people’s opinions and attitudes towards this tren is vary. Therefore, this research was conducted with the aim to knowing the public opinion subjectivity or sentiment analysis using Naïve Bayes (NB) and Support Vector Machine (SVM) algorithms. The classification method used is probability and statistical method which refers to Bayes theorem. There are three experimental scenarios, namely the split percentage 90:10; 80:20; and 70:30. The comparison of accuracy values is done using automatic labeling method. The results show that at split percentage of 90:10 an accuracy value is obtained 61% for NB algorithm and 78% for SVM algorithm. For the split percentage of 80:20 an accuracy value is obtained 63% for NB algorithm and 83% for SVM algorithm. As for the split percentage 70:30 an accuracy value is obtained 66% for NB algorithm and 83% for SVM algorithm. From these results, it can be concluded that the 70:30 split percentage model using the SVM algorithm is the best experimental scenario. Keywords: Sentiment Analysis, Social Media, E-Commerce, Naïve Bayes, Support Vector Machine Adanya pandemi Covid-19 yang mewabah di seluruh negara termasuk Indonesia, menyebabkan pemerintah membuat kebijakan Pembatasan Sosial Berskala Besar (PSBB) pada banyak bidang salah satunya ekonomi. Kebijakan tersebut memunculkan tren baru di masyarakat, yakni kebiasaan berbelanja online. Tren pembelian secara online melalui e-commerce semakin diminati karena e-commerce tidak segan memberikan potongan harga yang cukup besar serta gratis ongkos kirim. Meskipun demikian, pendapat dan sikap masyarakat akan tren ini berbedabeda. Oleh karena itu, penelitian ini dilakukan dengan tujuan untuk mengetahui subjektivitas opini masyarakat atau analisis sentimen dengan menggunakan algoritma Naïve Bayes (NB) dan Support Vector Machine (SVM). Metode pengklasifikasian yang digunakan adalah metode probabilitas dan statistik yang mengacu pada teorema Bayes. Terdapat tiga skenario eksperimen yaitu persentase split 90:10; 80:20; dan 70:30. Adapun pembandingan nilai akurasi dilakukan dengan menggunakan metode labeling otomatis. Hasil menunjukkan bahwa pada persentase split 90:10 diperoleh nilai akurasi sebesar 61% untuk algoritma NB dan 78% untuk algoritma SVM. Untuk persentase split 80:20 diperoleh nilai akurasi sebesar 63% untuk algoritma NB dan 83% untuk algoritma SVM. Sedangkan untuk persentase split 70:30 diperoleh nilai akurasi sebesar 66% untuk algoritma NB dan 83% untuk algoritma SVM. Dari hasi tersebut, dapat disimpulkan bahwa model persentase split 70:30 dengan menggunakan algoritma SVM adalah skenario eksperimen yang terbaik. Kata kunci: Analisa Sentimen, Media Sosial, E-commerce, Naïve Bayes, Support Vector Machine

Item Type:	Thesis (S1)
Call Number CD:	FIK/INFO. 22 194
NIM/NIDN Creators:	41519010008
Uncontrolled Keywords:	Analisa Sentimen, Media Sosial, E-commerce, Naïve Bayes, Support Vector Machine
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 100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 154 Subconscious and Altered States and Process/Psikologi Bawah Sadar > 154.6 Sleep Phenomena/Fenomena Tidur > 154.63 Dreams/Mimpi > 154.634 Analysis/Analisis 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma
Divisions:	Fakultas Ilmu Komputer > Informatika
Depositing User:	ADELINA HASNA SETIAWATI
Date Deposited:	24 Mar 2023 02:34
Last Modified:	24 Mar 2023 02:34
URI:	http://repository.mercubuana.ac.id/id/eprint/75376

Actions (login required)

View Item