IMPLEMENTASI MULTINOMIAL NAIVE BAYES UNTUK KLASIFIKASI SENTIMEN TERHADAP PELAYANAN PERUSAHAAN OTOBUS MENGGUNAKAN DATA FACEBOOK

PANGESTU, DONY JACARRIA (2022) IMPLEMENTASI MULTINOMIAL NAIVE BAYES UNTUK KLASIFIKASI SENTIMEN TERHADAP PELAYANAN PERUSAHAAN OTOBUS MENGGUNAKAN DATA FACEBOOK. S1 thesis, Universitas Mercu Buana Jakarta.

[img]
Preview
Text (HAL COVER)
01 COVER.pdf

Download (3MB) | Preview
[img]
Preview
Text (ABSTRAK)
02 ABSTRAK.pdf

Download (202kB) | Preview
[img] Text (BAB I)
03 BAB 1.pdf
Restricted to Registered users only

Download (967kB)
[img] Text (BAB II)
04 BAB 2.pdf
Restricted to Registered users only

Download (928kB)
[img] Text (BAB III)
05 BAB 3.pdf
Restricted to Registered users only

Download (1MB)
[img] Text (BAB IV)
06 BAB 4.pdf
Restricted to Registered users only

Download (314kB)
[img] Text (BAB V)
07 BAB 5.pdf
Restricted to Registered users only

Download (354kB)
[img] Text (BAB VI)
08 BAB 6.pdf
Restricted to Registered users only

Download (417kB)
[img] Text (DAFTAR PUSTAKA)
09 DAFTAR PUSTAKA.pdf
Restricted to Registered users only

Download (305kB)
[img] Text (LAMPIRAN)
10 LAMPIRAN.pdf
Restricted to Registered users only

Download (499kB)

Abstract

Customer satisfaction can be seen from the good and bad quality of service. many people use the social network facebook to expressive opinions. Sentiment analysis is a blend of data mining and text mining. Therefore, a collection of Facebook posts in the form of text is collected for processing so that it can be used for sentiment analysis. Use of multinomial Naïve Bayes algorithm to optimize sentiment data classification results. There are three classes used, namely negative, neutral, and positive. Before being classified, raw data goes through preprocessing stage first to normalize words in data. use of TF-IDF method helps for data weighting. it is necessary to share data in the classification stage, namely test data and training data. Which is where the test data is 20%, and the training data is 80%. Testing this data using a confusion matrix. percentage of sentiment data on otobus company services obtained from facebook. with a percentage of 23% negative sentiment, 53% neutral sentiment, and 25% positive sentiment. Can the key word that the service of the bus company is still considered neutral by custommers. From the results of the data test, the accuracy value is 95%, precision is 95%, and recall is 95%. This shows that the method used has a fairly good level.. Key words: sentiment, opinion, multinomial naïve bayes, facebook, universitas mercu buana Kepuasan pelanggan dapat dilihat dari baik buruknya kualitas pelayanan. banyak masyarakat yang menggunakan jejaring sosial facebook untuk mengekspresikan opini. Analisis sentimen adalah paduan dari data mining dan teks mining. Oleh karena itu kumpulan postingan facebook yang berupa teks dikumpulkan untuk selanjutnya di olah agar bisa digunakan untuk analisis sentiment. Penggunaan algoritma multinomial Naïve Bayes untuk mengoptimalkan hasil klasifikasi data sentiment. Ada tiga kelas yang digunakan, yaitu negative, netral, dan positif. Sebelum di klasifikasi, data mentah melewati tahap preprocessing terlebih dahulu untuk menormalisasi kata yang ada pada data. penggunaan metode TF-IDF membantu untuk pembobotan data. diperlukan pembagian data dalam tahap klasifikasi, yaitu data uji dan data latih. Yang dimana data uji 20%, dan data latih 80%. Pengujian data ini menggunakan confusion matrix. jumlah persentase data sentiment terhadap pelayanan perusahaan otobus yang didapatkan dari facebook. dengan persentase 23% sentiment negatif, 53% sentiment netral, dan 25% sentiment Positif. Bisa disimpulkan bahwa pelayanan perusahaan otobus tersebut masih di anggap netral oleh penggunanya. Dari hasil uji data diperoleh nilai akurasinya 95%, precision 95%, dan recall 95%. Penelitian ini menunjukan bahwa metode yang digunakan memiliki tingkatan cukup baik. Kata kunci: sentimen, opini, multinomial naïve bayes, facebook, universitas mercubuana

Item Type: Thesis (S1)
Call Number CD: FIK/INFO. 22 146
Call Number: SIK/15/22/039
NIM/NIDN Creators: 41516010127
Uncontrolled Keywords: sentimen, opini, multinomial naïve bayes, facebook, universitas mercubuana
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
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 > 006 Special Computer Methods/Metode Komputer Tertentu > 006.7 Multimedia Systems/Sistem-sistem Multimedia > 006.75 Social Multimedia/Multimedia Social > 006.754 Online Social Network/Situs Jejaring Sosial, Sosial Media
200 Religion/Agama > 260 Christian Social Theology/Teologi Sosial Kristen > 268 Religious Education/Pendidikan Agama Kristen, Pengajaran Agama Kristen > 268.7 Services/Pelayanan
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: 26 Oct 2022 06:21
Last Modified: 26 Oct 2022 06:21
URI: http://repository.mercubuana.ac.id/id/eprint/70956

Actions (login required)

View Item View Item