KLASIFIKASI UJARAN KEBENCIAN DI MEDIA SOSIAL APLIKASI X MENGGUNAKAN RANDOM FOREST DAN SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE)

YUSUF, MUHAMMAD and Yusliani, Novi and Satria, Hadipurnawan (2025) KLASIFIKASI UJARAN KEBENCIAN DI MEDIA SOSIAL APLIKASI X MENGGUNAKAN RANDOM FOREST DAN SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE (SMOTE). Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021382025126_COVER.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (347kB)
	Text RAMA_55201_09021382025126.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021382025126_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy
	Text RAMA_55201_09021382025126_0008118205_0018048003_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB)
	Text RAMA_55201_09021382025126_0008118205_0018048003_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (321kB) | Request a copy
	Text RAMA_55201_09021382025126_0008118205_0018048003_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (196kB) | Request a copy
	Text RAMA_55201_09021382025126_0008118205_0018048003_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021382025126_0008118205_0018048003_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (362kB) | Request a copy
	Text RAMA_55201_09021382025126_0008118205_0018048003_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (162kB) | Request a copy
	Text RAMA_55201_09021382025126_0008118205_0018048003_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (164kB) | Request a copy
	Text RAMA_55201_09021382025126_0008118205_0018048003_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (88kB) | Request a copy

Abstract

Classification is one of the fields of Natural Language Processing that automates the classification of text into one or more appropriate categories based on its content by building a model using training data. This study aims to classify hate speech tweets on application X using Random Forest and Synthetic Minority Oversampling Technique (SMOTE). The Random Forest approach is used because of its ability to handle classification problems on complex datasets and the SMOTE technique to overcome the imbalance of the majority and minority classes in a dataset of 3,300 data, namely 2000 hate tweets and 1300 nothate tweets. The highest accuracy results occurred in the Random Forest + SMOTE algorithm with an accuracy of 89,4%, a precision of 95,0%, a recall of 74,7%, and an f1-score of 83,6%. The influence of the SMOTE technique on the performance results of the Random Forest algorithm in classifying can be seen in the accuracy level of the best model without using SMOTE 81% while the best model using SMOTE 89.4% increased by 10.37%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Klasifikasi, Random Forest, dataset, Synthetic Minority Oversampling Technique, X, Tweet
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Yusuf
Date Deposited:	16 Apr 2025 06:43
Last Modified:	16 Apr 2025 06:43
URI:	http://repository.unsri.ac.id/id/eprint/170335

Actions (login required)

View Item