SENTIMEN ANALISIS KOMENTAR YOUTUBE MENGGUNAKAN ALGORITMA C4.5 DAN ADAPTIVE BOOSTING

ANGGARA, REDHA BAYU and Primartha, Rifkie and Jambak, Muhammad Ihsan (2019) SENTIMEN ANALISIS KOMENTAR YOUTUBE MENGGUNAKAN ALGORITMA C4.5 DAN ADAPTIVE BOOSTING. Undergraduate thesis, Sriwijaya University.

Preview	Text RAMA_55201_09021381419067_0001067709_0205046801_01_FRONT_REF.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_55201_09021381419067.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021381419067_0001067709_0205046801_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (292kB) | Request a copy
	Text RAMA_55201_09021381419067_0001067709_0205046801_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021381419067_0001067709_0205046801_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021381419067_0001067709_0205046801_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (425kB) | Request a copy
	Text RAMA_55201_09021381419067_0001067709_0205046801_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (269kB) | Request a copy
	Text RAMA_55201_09021381419067_0001067709_0205046801_07_REF.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (123kB) | Request a copy
	Text RAMA_55201_09021381419067_0001067709_0205046801_08_LAMP.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (488kB) | Request a copy
	Text RAMA_55201_09021381419067_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy

Abstract

Analisis sentimen merupakan bidang komputasi yang mempelajari suatu opini, sikap, atau emosi dari suatu entitas. Salah satu metode yang dapat digunakan pada analisis sentimenadalah Algoritma C4.5 yaitu algoritma klasifikasi pohon keputusan,. Dalam mengkontruksi pohon keputusan, Algoritma C4.5 membentuk pohon keputusan berdasarkan Gain Ratio. Dibutuhkan sebuah metode tambahan untuk mempelajari keterkaitan apa saja yang mempengaruhi data latih,agar algoritma C4.5 dapat bekerja lebih baik,salah satunya adalah algoritma AdaBoost(Adaptive Boosting). AdaBoostmengadopsi metode ensemble learning untuk membandingkan dan menggabungkan populasi kelas lemah dan kuat.Objek klasifikasi pada penelitan ini adalah sentimenkomentar pada video YouTube.Dalam proses klafiikasiakan dilakukan dalam dua tipe pengujian, komposisi kelas data trainingbalanced dan unbalanced.Hasil penelitian didapatkan bahwa Adaptive Boosting dapat meningkatkan akurasi algoritma C4.5 baik dalam data trainingbalanced maupun unbalanced.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	analisis sentimen, pemprosesan bahasa alami, algoritma c45, adabusst, klasifikasi, pembelajaran kelas lemah, komentar vidio youtube
Subjects:	T Technology > T Technology (General) > T58.5-58.64 Information technology > T58.5 General works Management information systems Cf. HD30.213 Industrial management Cf. HF5549.5.C6+ Communication in personnel management Cf. TS158.6 Automatic data collection systems (Production control)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Users 1484 not found.
Date Deposited:	27 Aug 2019 08:49
Last Modified:	27 Aug 2019 08:49
URI:	http://repository.unsri.ac.id/id/eprint/4913

Actions (login required)

View Item