sentiment analysis pada review restoran …eprints.umm.ac.id/40062/1/pendahuluan.pdftak lupa...
TRANSCRIPT
i
SENTIMENT ANALYSIS PADA REVIEW RESTORAN
MENGGUNAKAN NAÏVE BAYES DAN STANFORD NER
Laporan Tugas Akhir
Diajukan Untuk Memenuhi
Persyaratan Guna Meraih Gelar Sarjana Sastra I
Teknik Informatika Universitas Muhammadiyah Malang
Mohammad Fadhil
201210370311190
JURUSAN TEKNIK INFORMATIKA
FAKULTAS TEKNIK
UNIVERSITAS MUHAMMADIYAH MALANG
FEBRUARI 2018
i
ii
iii
iv
KATA PENGANTAR
ASSALAMUALAIKUM, WR WB.
Puji syukur ke hadirat ALLAH SWT atas limpahan rahmat, petunjuk dan hidayahnya
kepada penulis sehingga penulis dapat menyelesaikan Tugas Akhir yang berjudul “Analysis
Sentiment pada Review Restoran Menggunakan Naïve bayes dan Stanford NER” .
Tak lupa shalawat, salam serta taslim kepada baginda Besar, Nabi Muhammad SAW,
karna dengan cerminan semangatnyalah penulis dapat menjalani hari-hari dalam
menyelesaikan Tugas Akhir di Tekhnik Informatika Universitas Muhammadiyah Malang.
Dengan segala kerendahan hati, penulis menyadari bahwa dalam penyelesaian Tugas
Akhir ini tidak lepas dari peran berbagai pihak yang telah banyak memberikan bantuan,
bimbingan dan dukungan. Dalam kesempatan ini penulis ingin mengucapkan terima kasih yang
tak terhingga kepada :
1. Bapak Yuda Munarko, S.Kom., M.Sc selaku dosen pembimbing I yang telah
memberikan pengarahan, bimbingan, serta masukan selama pelaksanaan tugas akhir
dan penelitian serta penulisan laporan.
2. Bapak Yufis Azhar, S.Kom., M.Kom selaku dosen pembimbing II yang telah
memberikan pengarahan, bimbingan, serta masukan selama pelaksanaan tugas akhir
dan penelitian serta penulisan laporan.
3. Keluarga, Bapak saya Dr. Ir. Mustaring M.P., Ibu tercinta Ir. Sri Nurvita Suratinoyo,
dan kakak saya Rizki Amalia S.Si, M.Ak., yang tak henti-hentinya memberikan cahaya
doa penuh kasih sayang, semangat, dan motivasi kepada saya selaku penulis
4. Sahabat dan teman teman saya dengan segala rasa yang pernah menemani, berkat
mereka lah saya mampu menghadapi hari berat maupun bahagia saya di kota malang .
5. Dan segala pihak.
v
vi
Daftar Isi
LEMBAR PERSETUJUAN .................................................................................................................. i
LEMBAR PENGESAHAN .................................................................................................................. ii
LEMBAR PERNYATAAN ..................................................................................................................iii
Abstrak ................................................................................................................................................. iv
Abstract................................................................................................................................................. v
KATA PENGANTAR .......................................................................................................................... vi
1 BAB I PENDAHULUAN ............................................................................................................. 1
1.1 Latar Belakang ...................................................................................................................... 1
1.2 Rumusan Masalah ................................................................................................................. 2
1.3 Tujuan ................................................................................................................................... 2
1.4 Batasan Masalah ................................................................................................................... 3
1.5 Metodelogi Penelitian ........................................................................................................... 3
1.6 Sistematika Penulisan............................................................................................................ 4
2 BAB II LANDASAN TEORI ....................................................................................................... 5
2.1 Text Mining .......................................................................................................................... 5
2.2 Sentiment Analysis ............................................................................................................... 5
2.3 Text Preporcessing ................................................................................................................ 6
2.4 Klasifikasi ............................................................................................................................. 6
2.5 Naïve Bayes .......................................................................................................................... 6
2.6 Stanford NER ........................................................................................................................ 7
2.7 Teknik Pengujian .................................................................................................................. 9
2.7.1 Recall ............................................................................................................................ 9
2.7.2 Presisi ............................................................................................................................ 9
2.7.3 Accuracy ....................................................................................................................... 9
3 BAB III ANALISA DAN PERANCANGAN ............................................................................. 10
3.1 Data ..................................................................................................................................... 10
3.1.1 Pengumpulan Data ...................................................................................................... 10
3.1.2 Analisa Data ................................................................................................................ 10
3.2 Perancangan Sistem ............................................................................................................ 11
3.2.1 Analisa Pembuatan Model NER Berdasarkan Review Restoran ................................. 13
vii
3.2.2 Analisa Sentiment Berdasarkan Review Restoran ....................................................... 19
3.3 Analisa Metode Naïve Bayes Model Multinomial Text ...................................................... 23
4 BAB IV HASIL DAN PENGUJIAN .......................................................................................... 26
4.1 Implementasi Sistem ........................................................................................................... 26
4.1.1 Perangkat Keras .......................................................................................................... 26
4.1.2 Perangkat Lunak.......................................................................................................... 26
4.2 Implementasi Model NER ................................................................................................... 26
4.3 Implementasi Pengujian metode Naïve Bayes Model Multinomial Pada Weka .................. 29
4.3.1 Pengujian Supplied Test Pada Weka ........................................................................... 30
4.3.2 Pengujian 10 Fold Cross Validation Pada Weka ......................................................... 36
4.4 Implementasi Program ........................................................................................................ 38
4.4.1 Hasil Resume Implementasi Program ......................................................................... 42
4.4.2 Pengujian dan Hasil Implementasi Program ................................................................ 42
5 BAB V PENUTUP ..................................................................................................................... 44
5.1 Kesimpulan ......................................................................................................................... 44
5.2 Saran ................................................................................................................................... 44
Daftar Pustaka ..................................................................................................................................... 45
viii
Daftar Gambar
gambar 3 1 Alur Perancangan Sistem ................................................................................................. 11
gambar 3 2 Alur Perancangan Model NER ......................................................................................... 14
gambar 3 3 Data Sebelum Di lakukan Tagging ................................................................................... 14
gambar 3 4 Data Setelah DI lakukan Tagging ..................................................................................... 15
gambar 3 5 Comand Pembuatan File.Tok ........................................................................................... 16
gambar 3 6 Bentuk File.Tok ............................................................................................................... 16
gambar 3 7 Penghilangan Slash File.tok ............................................................................................. 17
gambar 3 8 Tampilan File.Props yang telah DI ubah .......................................................................... 18
gambar 3 9 Comand Pembuatan File Props ........................................................................................ 18
gambar 3 10 Tampilan Awal Weka..................................................................................................... 19
gambar 3 11 Persiapan Preprocess Pada Weka ................................................................................... 20
gambar 3 12 Data Training Set ........................................................................................................... 21
gambar 3 13 Data Training Sebelum Di lakukan Teknik SMOTE ...................................................... 21
gambar 3 14 Konfigurasi SMOTE ...................................................................................................... 22
gambar 3 15 Data Training Setelah DI lakukan Teknik SMOTE ........................................................ 22
gambar 3 16 Pemilihan Metode Klasifikasi ........................................................................................ 23
gambar 4 1 Membuka File .................................................................................................................. 27
gambar 4 2 Membuka Model NER ..................................................................................................... 28
gambar 4 3 Hasil Penguian NER ........................................................................................................ 29
gambar 4 4 Pengujian Supplied Test Resto 1 ...................................................................................... 30
gambar 4 5 Hasil Pengujian Supplied Test Resto 1 ............................................................................. 31
gambar 4 6 Pengujian Supplied Test Resto 2 ...................................................................................... 32
gambar 4 7 Hasil Pengujian Supplied Test Resto 2 ............................................................................. 32
gambar 4 8 Pengujian Supplied test Resto 3 ....................................................................................... 33
gambar 4 9 Hasil Pengujian Supplied Test Resto 3 ............................................................................. 34
gambar 4 10 Pengujian Supplied Test Resto 4 .................................................................................... 35
gambar 4 11 Hasil Pengujian Supplied Test Resto 3 ........................................................................... 35
gambar 4 12 Data Setelah Di lakukan Teknik SMOTE....................................................................... 37
gambar 4 13 Pemilihan Teknik Pengujian Pada Weka ........................................................................ 37
gambar 4 14 Hasil Pengujian 10 Fold Cross Validation ...................................................................... 38
gambar 4 15 Tampilan Awal Eclipse .................................................................................................. 39
gambar 4 16 Code Program Memanggil File ...................................................................................... 39
gambar 4 17 Code Program Kalkulasi Probabilitas ............................................................................. 40
gambar 4 18 Code Program Perangkuman Data Keseluruhan ............................................................. 41
gambar 4 19 Data Keseluruhan Yang Akan Di rangkum .................................................................... 42
gambar 4 20 Bagan Data Uji ............................................................................................................... 43
ix
Daftar Table
table 2 1 Bentuk Umum Aturan NER ................................................................................................... 8
table 2 2 Aturan NER Terkait Penelitian............................................................................................... 8
table 2 3 Teknik Pengujian ................................................................................................................... 9
tabel 3 1 Pembagian Data Keseluruhan ............................................................................................... 11
tabel 3 2 Bentuk Aturan Umum NER ................................................................................................. 12
tabel 3 3 Aturan NER Terkait Penelitian............................................................................................. 12
tabel 3 4 Penjelasan SIngkat Naive Bayes Multinomial ...................................................................... 24
tabel 4 1 Rata-Rata AKurasi Pengujian Supplied Test ........................................................................ 36
tabel 4 2 Hasil Resume Program ......................................................................................................... 42
tabel 4 3 Pengujian Program ............................................................................................................... 43
45
Daftar Pustaka
[1] Thomas Stefanus Kaihatu, “Analisa Kesenjangan Kualitas Pelayanan Dan Kepuasan
Konsumen Pengunjung Plaza Tunjungan Surabaya,” J. Manaj. dan Kewirausahaan, vol.
10, no. October, p. pp.66-83, 2008.
[2] V. Christanti, M. Jeanny, and P. Sakti, “Naive Bayes Classification in The Question and
Answering System,” no. Icisbc, pp. 139–144, 2013.
[3] S. Wardoyo, W. Maharani, and A. P. Kurniati, “Opinion Summarization Fitur Produk
Elektronik Pada Amazon . Com Dengan Metode Maximum Entropy,” 2012.
[4] D. A. Muthia, “ANALISIS SENTIMEN PADA REVIEW RESTORAN DENGAN
TEKS BAHASA INDONESIA MENGUNAKAN,” vol. 2, no. 2, pp. 39–45, 2017.
[5] I. F. Rozi, S. H. Pramono, and E. A. Dahlan, “Implementasi Opinion Mining ( Analisis
Sentimen ) untuk Ekstraksi Data Opini Publik pada Perguruan Tinggi,” Electr. Power,
Electron. Commun. Control. Informatics Semin., vol. 6, no. 1, pp. 37–43, 2012.
[6] G. Asrofi, B. Universitas, M. Ponorogo, and G. A. Buntoro, “Analisis Sentimen Calon
Gubernur DKI Jakarta 2017 Di Twitter Analisis Sentimen Calon Gubernur DKI Jakarta
2017 Di Twitter,” no. March, 2017.
[7] H. Cui, V. Mittal, and M. Datar, “Comparative Experiments on Sentiment Classification
for Online Product Reviews,” pp. 1265–1270, 2003.
[8] D. Menggunakan and S. Ner, “PEMBUATAN MODEL NAMED ENTITY
RECOGNITION UNTUK TWITTER BAHASA INDONESIA,” pp. 2–5.
[9] S. Blair-goldensohn et al., “Building a Sentiment Summarizer for Local Service
Reviews,” 2008.
[10] A. Trilla and F. Alıas, “Sentiment analysis of twitter messages based on multinomial
naive Bayes,” Comput. Surv, 2012.