KLASIFIKASI ULASAN PALSU MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM)

SETYAWAN, FRANSISKA KRISTINA and Utami, Alvi Syahrini and Saputra, Danny Matthew (2023) KLASIFIKASI ULASAN PALSU MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282025074.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (17MB) | Request a copy
	Text RAMA_55201_09021282025074_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021282025074_0022127804_0010058507_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB)
	Text RAMA_55201_09021282025074_0022127804_0010058507_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282025074_0022127804_0010058507_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282025074_0022127804_0010058507_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021282025074_0022127804_0010058507_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282025074_0022127804_0010058507_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (334kB) | Request a copy
	Text RAMA_55201_09021282025074_0022127804_0010058507_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (447kB) | Request a copy
	Text RAMA_55201_09021282025074_0022127804_0010058507_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy

Abstract

Customer reviews play a crucial role in shaping purchasing decisions. The significance of these reviews has led many individuals to create fake reviews purposely for personal gain. Fake reviews can result in unhealthy business competition, damage a business's reputation which leads to financial losses, and diminish consumer trust. This research aims to classify reviews into fake and genuine categories. This research utilizes the Support Vector Machine (SVM) method to classify data due to SVM's advantages in handling datasets with many features. The research integrates features including review helpful, sentiment, subjectivity, word count, noun count, adjective count, verb count, adverb count, authenticity, and analytical thinking. Testing is conducted using data split ratios of 60:40, 70:30, 80:20, and 90:10, with parameter C values set at 0.1, 1, and 10 for each split ratio. The research findings indicate that the SVM model for classifying fake reviews, with a dataset split ratio of 70:30 for training and testing and a C value of 1, demonstrates the best performance in terms of accuracy, precision, and F-Measure, achieving 95.2%, 97.62%, and 95.60%, respectively.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Klasifikasi, Support Vector Machine
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Fransiska Kristina Setyawan
Date Deposited:	09 Jan 2024 05:24
Last Modified:	09 Jan 2024 05:24
URI:	http://repository.unsri.ac.id/id/eprint/137750

Actions (login required)

View Item