ANALISIS SENTIMEN TERHADAP ISU KHILAFAH PADA MEDIA SOSIAL TWITTER MENGGUNAKAN ALGORITME K-NEAREST NEIGHBORS DAN SUPPORT VECTOR MACHINE

Fares Analis Syahad, NIM.: 17106050033 (2023) ANALISIS SENTIMEN TERHADAP ISU KHILAFAH PADA MEDIA SOSIAL TWITTER MENGGUNAKAN ALGORITME K-NEAREST NEIGHBORS DAN SUPPORT VECTOR MACHINE. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (ANALISIS SENTIMEN TERHADAP ISU KHILAFAH PADA MEDIA SOSIAL TWITTER MENGGUNAKAN ALGORITME K-NEAREST NEIGHBORS DAN SUPPORT VECTOR MACHINE) 17106050033_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (1MB) | Preview
	Text (ANALISIS SENTIMEN TERHADAP ISU KHILAFAH PADA MEDIA SOSIAL TWITTER MENGGUNAKAN ALGORITME K-NEAREST NEIGHBORS DAN SUPPORT VECTOR MACHINE) 17106050033_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

In June 2022 in Indonesia there was an arrest by the police of the head of the Khilafatul Muslimin community organization on the grounds that the activities of the Khilafatul Muslimin group were not in accordance with the value of Pancasila and threatened the integrity of the Unitary State of the Republic of Indonesia. This resulted in the khilafah issue becoming a hot topic of discussion on social media, especially on social media Twitter. Twitter users discuss this issue a lot with their various opinions, both opinions that have positive, neutral and negative sentiments. This research aims to analyze the sentiment of twitter netizens about the issue with text mining. In this research, the Machine Learning algorithms used are K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) and the data used contains the word "khilafah" obtained using the crawling method. The data is 3630 tweet data with labels and 397 tweet data without labels. Data analysis uses confusion matrix and k-fold cross validation. The results of this study can be concluded that the SVM method is better than KNN with the accuracy value using confusion matrix is 87% for SVM and 56% for KNN and the average accuracy value using kfold cross validation is 60% for SVM and 58% for KNN. The results of the SVM model implementation on 397 unlabeled data are 241 tweets (60.71%) positive sentiment, 107 tweets (26.95%) neutral sentiment and 49 tweets (12.34%) negative sentiment. While the implementation using KNN resulted in 220 tweets (55.42%) positive sentiment, 94 tweets (23.68%) neutral sentiment and 83 tweets (20.91%) negative sentiment. From these statistics it can be concluded that the sentiment of twitter netizens on the issue of khilafah tends to be positive.

Share this knowledge with your friends :

Actions (login required)

View Item