Image of OPTIMASI ALGORITMA SUPPORT VECTOR MACHINE (SVM) DENGAN PARTICLE SWARM OPTIMIZATION (PSO) UNTUK KLASIFIKASI MULTI-CLASS PADA X (TWITTER)

Skripsi

OPTIMASI ALGORITMA SUPPORT VECTOR MACHINE (SVM) DENGAN PARTICLE SWARM OPTIMIZATION (PSO) UNTUK KLASIFIKASI MULTI-CLASS PADA X (TWITTER)

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

X (Twitter), with 237.8 million daily active users mostly aged 18 to 29, has become one of the largest and most influential communication platforms in the world. However, despite its potential as a tool for information sharing and interaction, X (Twitter) also presents major challenges in terms of online behavior. One of the main problems that has emerged is the rise of hate speech, which can damage the community atmosphere and create an unhealthy digital environment. This research classifies Indonesian hate speech tweets on X using Support Vector Machine (SVM) model and Particle Swarm Optimization (PSO) optimization algorithm to produce effective classification results from the text. The main objective of this research is to develop a system that can classify hate speech tweets with good and accurate accuracy, and compare the performance of the SVM model before and after being optimized with PSO. The dataset used in this research includes 1,000 hate speech tweets with 4 label classes, namely religious hate speech as much as 403 data, racial hate speech 318 data, physical hate speech 168 data, and gender hate speech 111 data. The processes in this research are data pre-processing, TF-IDF, and classification analysis with SVM and PSO. SVM accuracy value without PSO is 74.56%, SVM accuracy value optimized by PSO is 88.25%. This shows that parameter optimization using PSO can improve the performance of SVM models in text classification tasks.

Availability
Inventory Code Barcode Call Number Location Status
2407006913T162197T1621972024Central Library (REFERENCE)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1621972024
Publisher
Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
xiv, 58 hlm.; ilus.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
006.310 7
Content Type
Text
Media Type
unmediated
Carrier Type
-
Edition
-
Subject(s)
Machine Learning
Prodi Teknik Informatika
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment