PERBANDINGAN ALGORITMA NAÏVE BAYES DAN EXTREME GRADIENT BOOSTING (XGBOOST) PADA ANALISA SENTIMEN TERHADAP KEPUASAN KINERJA TIMNAS SEPAK BOLA INDONESIA

AZIZ, HAFIEF MAULANA (2022) PERBANDINGAN ALGORITMA NAÏVE BAYES DAN EXTREME GRADIENT BOOSTING (XGBOOST) PADA ANALISA SENTIMEN TERHADAP KEPUASAN KINERJA TIMNAS SEPAK BOLA INDONESIA. S1 thesis, Universitas Mercu Buana Jakarta.

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

Download (414kB) | Preview
[img]
Preview
Text (ABSTRAK)
02 Abstrak.pdf

Download (23kB) | Preview
[img] Text (BAB I)
03 Bab 1.pdf
Restricted to Registered users only

Download (77kB)
[img] Text (BAB II)
04 Bab 2.pdf
Restricted to Registered users only

Download (34kB)
[img] Text (BAB III)
05 Bab 3.pdf
Restricted to Registered users only

Download (211kB)
[img] Text (BAB IV)
06 Bab 4.pdf
Restricted to Registered users only

Download (564kB)
[img] Text (BAB V)
07 Bab 5.pdf
Restricted to Registered users only

Download (18kB)
[img] Text (DAFTAR PUSTAKA)
08 Daftar Pustaka.pdf
Restricted to Registered users only

Download (72kB)
[img] Text (LAMPIRAN)
09 Lampiran.pdf
Restricted to Registered users only

Download (955kB)

Abstract

Football is the number one sport in the world and Indonesia itself is no exception, and the assessment of a football team is very important to be carried out to become the main parameter in evaluating for the future. PSSI as the supreme parent of Indonesian Football only evaluates team performance from the level of achievement and observations from PSSI elected people, namely PSSI Exco Members. The lack of involvement of information technology such as Machine Learning in assessing the performance of soccer teams is a problem for PSSI. So far, Indonesian Football supporters have not been involved in evaluating the performance of the Indonesian National Team. Even though the assessment of football supporters can be an alternative parameter in evaluating the performance of the Indonesian National Team. So this research was conducted to find alternative methods in evaluating the Indonesian Football National Team by utilizing Machine Learning technology. To find the best Machine Learning algorithm, a comparison of the algorithms used is carried out. In this study, a comparison of the Naïve Bayes and Extreme Gradient Boosting (XGBoost) algorithms was carried out in the sentiment analysis of Indonesian netizens' tweets on the performance of the Indonesian Football National Team. By using several Natural Language Processing (NLP) methods for text processing and extraction features for word weighting, good results are obtained from the two algorithm models used with an average accuracy value of ±85%, where the XGBoost algorithm has higher accuracy. better with an average accuracy value of 85.48% compared to Naïve Bayes which has an average accuracy value of 84.20%. Keywords: sentiment analisys, Naïve Bayes, xgboost, football, and indonesia Sepak Bola menjadi olahraga nomor satu di dunia dan tidak terkecuali di Indonesia sendiri, dan penilaian terhadap sebuah tim Sepak Bola sangatlah penting dilakukan untuk menjadi parameter utama dalam melakukan evaluasi untuk kedepannya. PSSI selaku induk tertinggi Sepak Bola Indonesia hanya mengevalusai kinerja tim dari tingkat prestasinya dan pengamatan dari orang-orang terpilih PSSI yaitu Anggota Exco PSSI. Kurangnya keterlibatan teknologi informasi seperti Machine Learning dalam penilaian kinerja tim Sepak Bola menjadi permasalahan sendiri bagi PSSI. Sejauh ini pendukung Sepak Bola Indonesia belum dilibatkan dalam penilaian kinerja Tim Nasional Indonesia. Padahal penilaian pendukung Sepak Bola bisa menjadi alternatif parameter dalam mengevaluasi kinerja Tim Nasional Indonesia. Jadi dilakukannya penelitian ini adalah untuk mencari metode alternatif dalam melakukan evaluasi terhadap Timnas Sepak Bola Indonesia dengan pemanfatan teknologi Machine Learning. Untuk mencari algortima Machine Learning yang terbaik dilakukan perbandingan dari algoritma yang dipakai. Dalam penelitian ini dilakukan perbadingan algoritma Naïve Bayes dan Extreme Gradient Boosting (XGBoost) pada analisis sentimen cuitan netizen Indonesia terhadap kinerja Timnas Sepak Bola Indonesia. Dengan menggunakan beberapa metode Natural Language Processing (NLP) untuk teks processing dan fitur ekstrasi untuk pembobotan kata, didapat hasil yang cukup baik dari kedua buah model algoritma yang dipakai dengan nilai rata-rata akurasi mecapai ±85%, dimana algortima XGBoost memiliki akurasi yang lebih baik dengan nilai ratarata akurasi 85,48% ketimbang Naïve Bayes yang memiliki nilai rata-rata akurasi 84,20%. Katakunci : analisis sentimen, Naïve Bayes, xgboost, sepak bola, dan indonesia

Item Type: Thesis (S1)
Call Number CD: FIK/INFO. 22 192
Call Number: SIK/15/23/016
NIM/NIDN Creators: 41519010163
Uncontrolled Keywords: analisis sentimen, Naïve Bayes, xgboost, sepak bola, dan indonesia
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
700 Arts/Seni, Seni Rupa, Kesenian > 790 Recreational and Performing Arts/Olah Raga dan Seni Pertunjukan > 796 Athletic and Outdoor Sports/Atletik dan Olah Raga Luar Ruangan
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: ADELINA HASNA SETIAWATI
Date Deposited: 24 Mar 2023 01:42
Last Modified: 24 Mar 2023 01:42
URI: http://repository.mercubuana.ac.id/id/eprint/75274

Actions (login required)

View Item View Item