Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JURNAL TEKNOLOGI DAN OPEN SOURCE
Mhd. Furqan
Department of Computer Science, Universitas Islam Negeri Sumatera Utara
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Sentiment Analysis of Loudspeaker Regulations in Houses of Worship on Social Media Using Support Vector Machine Algorithm Selly Novia Manihuruk; Mhd. Furqan; Aidil Halim Lubis
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4043

Abstract

Social media is an online platform where users can share content or interact with each other through discussions and debates that involve sentiments, such as agreement or disagreement on various topics. User sentiments on social media can be utilized in multiple ways, such as to gauge public opinion regarding the issuance of Circular Letter Number SE 05 of 2022 by the Ministry of Religious Affairs, which provides guidelines for the use of loudspeakers in mosques and prayer rooms. Due to the high volume of comments on social media regarding this circular, a sentiment analysis system is necessary. The sentiment analysis system in this research employs the Support Vector Machine (SVM) algorithm to classify comments as positive or negative. A total of 350 comments were collected from each social media platform—Facebook, Twitter, YouTube, and Instagram—about the issuance of the circular. These comments were divided into 250 for training data and 100 for testing data on each platform. The training data from all platforms were combined, resulting in a total of 1000 training data. Based on system testing using the Support Vector Machine algorithm, the accuracy achieved was 72%. This result reflects the system's capability to analyze sentiments related to the guidelines for using loudspeakers in mosques and prayer rooms as stated in the circular
Sentiment Analysis Related To Covid-19 Vaccination On Social Media Using The K-Nearest Neighbor (K-NN) Method Amanda Novrianty; Mhd. Furqan; Sriani Sriani
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4156

Abstract

Coronavirus 19 (COVID-19) has become a topic of great concern in the past two years. To anticipate the spread of the virus, the government has made various efforts, one of which is by procuring a COVID-19 vaccination to increase the body's immunity. In carrying out the program, the government urges the public to use social media as a means of disseminating information regarding the COVID-19 vaccination. Facebook is one of the most popular social media and is chosen by agencies as a medium of information. Information regarding the vaccination is shared by the Ministry of Health of the Republic of Indonesia through its Facebook Page and the public can provide opinions in the form of comments. Given that the comments are numerous and lengthy if you have to read the manual, it is difficult to classify which one corresponds to the positive, negative or neutral opinion class, so a system is needed to analyze them. This sentiment analysis system uses the K-Nearest Neighbor (K-NN) method to classify positive, negative and neutral opinions. This study uses 750 comments obtained from posts in November 2021 with the keywords 'vaccination' and 'vaccine', with the distribution of 700 training data and 50 test data. Furthermore, the comments are pre-processed with the stages of case folding, filtering, tokenizing, normalization, stopwords and stemming, then weighted using the TF-IDF feature. System testing is carried out using the K-Nearest Neighbor (K-NN) method with a value of k = 1, k = 3, k = 5, k = 7 and k = 9 . 1 and f-measure of 0.71428571428571. Meanwhile, the lowest accuracy value is at the value of k = 7 and k = 9 with an accuracy of 0.66 and an error rate of 0.34.
Co-Authors Aidil Halim Lubis Amanda Novrianty Selly Novia Manihuruk Sriani Sriani