Klasifikasi kalimat ofensif di media sosial twitter menggunakan algoritma Support Vector Machine (SVM) berbasis Particle Swarm Optimization (PSO)

Barizi, Ahmad (2023) Klasifikasi kalimat ofensif di media sosial twitter menggunakan algoritma Support Vector Machine (SVM) berbasis Particle Swarm Optimization (PSO). Sarjana thesis, UIN Sunan Gunung Djati Bandung.

Preview	Text (COVER) 1_cover.pdf Download (215kB) | Preview
Preview	Text (ABSTRAK) 2_abstrak(3).pdf Download (109kB) | Preview
Preview	Text (DAFTAR ISI) 3_daftarisi_7(1).pdf Download (118kB) | Preview
Preview	Text (BAB I) 4_bab1.pdf Download (257kB) | Preview
	Text (BAB II) 5_bab2.pdf Restricted to Registered users only Download (455kB) | Request a copy
	Text (BAB III) 6_bab3.pdf Restricted to Registered users only Download (416kB) | Request a copy
	Text (BAB IV) 7_bab4.pdf Restricted to Registered users only Download (830kB) | Request a copy
	Text (BAB V) 8_bab5.pdf Restricted to Registered users only Download (239kB) | Request a copy
	Text (DAFTAR PUSTAKA) 9_daftarpustaka.pdf Restricted to Registered users only Download (242kB) | Request a copy

Abstract

Twitter is one of the most popular and frequently used social media in Indonesia. Twitter allows users to express their opinions anonymously, without any restrictions on the language or content of the messages they share. This causes freedom of expression, and often offensive, soothing, and soothing sentences appear. The problem of offensive sentences on Twitter needs serious attention, and an effective solution is needed to overcome this. One solution is to use NLP technologies, such as offensive sentence classification. The method used in this study is text classification using the Support Vector Machine (SVM) algorithm with the application of the Particle Swarm Optimization (PSO) parameter optimization method. This study aims to build an offensive sentence classification model and compare the classification model with and without the application of parameter optimization. The results of the study using the split method show that modeling with SVM produces an accuracy above 70% for each dataset used. The application of PSO for parameter optimization can improve classification performance by increasing the classification accuracy.

Actions (login required)

View Item