ANALISIS SENTIMEN KEPUASAN MASYARAKAT TERHADAP KINERJA EKSPEDISI DI INDONESIA

RASYID, MUHAMMAD RADIAN (2023) ANALISIS SENTIMEN KEPUASAN MASYARAKAT TERHADAP KINERJA EKSPEDISI DI INDONESIA. S1 thesis, Universitas Mercu Buana Jakarta.

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

Download (628kB) | Preview
[img]
Preview
Text (ABSTRAK)
02 Abstrak.pdf

Download (99kB) | Preview
[img] Text (BAB I)
03 Bab 1.pdf
Restricted to Registered users only

Download (171kB)
[img] Text (BAB II)
04 Bab 2.pdf
Restricted to Registered users only

Download (189kB)
[img] Text (BAB III)
05 Bab 3.pdf
Restricted to Registered users only

Download (219kB)
[img] Text (BAB IV)
06 Bab 4.pdf
Restricted to Registered users only

Download (497kB)
[img] Text (BAB V)
07 Bab 5.pdf
Restricted to Registered users only

Download (100kB)
[img] Text (DAFTAR PUSTAKA)
08 Daftar Pustaka.pdf
Restricted to Registered users only

Download (147kB)
[img] Text (LAMPIRAN)
09 Lampiran.pdf
Restricted to Registered users only

Download (3MB)

Abstract

The main objective of this study is to compare Multinomial Naive Bayes and Adaptive Boosting algorithm performance that used individually to new proposed method Bagging Classifier that in theory can improve the performance of two algorithms. Dataset was taken from Twitter using username as the search query. The dataset was tested using three algorithms and then compared the best overall performance of the three, using automatic labelling and word cloud to detect words that frequently occurs in dataset. The best result was obtained by using Bagging Classifier algorithm with an accuracy rate of 96.69% dan an f1-score of 96.64%. Keywords: Sentiment Analysis, Bagging Classifier, Natural Language Processing. Tujuan utama dari penelitian ini adalah membandingkan algoritma Multinomial Naive Bayes dan Adaptive Boosting yang digunakan masing-masing dengan Bagging Classifier yang mampu meningkatkan kinerja dari kedua algoritma tersebut. Dataset diambil dari Twitter dengan menggunakan username sebagai search query. Dataset diuji dengan menggunakan tiga algoritma tersebut lalu membandingkan performa terbaik dari ketiganya, digunakan label automatis dan word cloud untuk mendeteksi kata yang sering muncul di dalam dataset. Hasil terbaik diperoleh dengan menggunakan algoritma Bagging Classifier dengan tingkat akurasi sebesar 96.69% dan f1-score sebesar 96.64%. Kata kunci : Analisis Sentimen, Bagging Classifier, Natural Language Processing

Item Type: Thesis (S1)
Call Number CD: FIK/SI. 23 002
Call Number: SIK/15/23/021
NIM/NIDN Creators: 41519010011
Uncontrolled Keywords: Analisis Sentimen, Bagging Classifier, Natural Language Processing
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
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
600 Technology/Teknologi > 650 Management, Public Relations, Business and Auxiliary Service/Manajemen, Hubungan Masyarakat, Bisnis dan Ilmu yang Berkaitan > 657 Accounting/Akuntansi > 657.8 Accounting for Enterprises Enganged in Specific Kinds of Activities/Akuntansi Usaha yang Bergerak dalam Jenis Kegiatan Tertentu > 657.83 Service and Professionals Activities/Kegiatan Pelayanan dan Profesional
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: ADELINA HASNA SETIAWATI
Date Deposited: 04 Apr 2023 07:08
Last Modified: 04 Apr 2023 07:08
URI: http://repository.mercubuana.ac.id/id/eprint/76052

Actions (login required)

View Item View Item