Claim Missing Document
Check
Articles

Found 4 Documents
Search
Journal : Indonesian Journal on Data Science

Sentiment Analysis Related National Social Security Agency for Employment in Indonesia: Hybrid Method Using Lexicon Based and Naive Bayes Classifier Approaches Rizky Fauzi Akbar; Habibi, Muhammad
INDONESIAN JOURNAL ON DATA SCIENCE Vol 1 No 1 (2023): Indonesian Journal on Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v1i1.896

Abstract

The National Social Security Agency (BPJS) for Employment is the Social Security Administering Agency with the goal of ensuring that each participant or member of the family receives adequate necessities. In its implementation, there is information that is spread, particularly on Twitter, regarding the Ministry of Health's decision, namely regarding Old Age Security (JHT), which can only be distributed/taken after the participant turns 56 years old, causing both pros and cons among the public. Based on unanalyzed tweets on Twitter, it is necessary to do extensive research to collect relevant information based on netizens' viewpoints. This research describes sentiment analysis of tweets from Twitter using the terms JHT, BPJSTK, and BPJS, which yield 4154 data tweets. We employ two approaches in this study: Lexicon Based and Nave Bayes Classifier. According to this study, the accuracy of the testing data is 92% for the Lexicon Based and 95% for the Nave Bayes Classifier. This study concluded that the JHT at BPJS Employment received unfavorable attitudes and negative reactions among users who addressed the rejection of new restrictions where JHT, could only be dispensed or taken when participants at BPJS Employment were 56 years old.
Pemetaan Opini Publik Menggunakan Data Mining: Studi Kasus Naturalisasi Pemain Sepak Bola dengan K-Means dan Naive Bayes Classifier Tegar Agustian; Fresia Nandela, Emilia; A. Sinay, Stani; Habibi, Muhammad
INDONESIAN JOURNAL ON DATA SCIENCE Vol 2 No 1 (2024): Indonesian Journal on Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Naturalisasi merupakan salah satu proses yang dilakukan oleh warga asing agar menjadi Warga Negara Indonesia (WNI) yang sah di mata hukum. Saat ini Timnas Indonesia memiliki beberapa pemain naturalisasi . Beberapa kalangan menyambut positif kehadiran mereka, melihatnya sebagai langkah strategis untuk meningkatkan kualitas dan daya saing tim. Namun, ada pula yang merasa skeptis dan meragukan keberlanjutan dukungan terhadap pemain lokal. Data yang diambil dari 3584 komentar YouTube melalui YouTube Data API mencerminkan keragaman opini yang dapat memberikan gambaran lebih mendalam tentang dinamika pandangan publik. Penelitian ini penting dalam konteks pemahaman pandangan masyarakat terhadap naturalisasi pemain sepak bola Timnas. Dengan menggunakan teknik Data Mining, terutama K-Means Clustering dan Naive Bayes Classifier, penelitian ini memberikan wawasan mendalam tentang kelompok-kelompok masyarakat dengan perspektif serupa atau berbeda terkait isu tersebut. Hasil dari proses K-Means Clustering digunakan sebagai label awal untuk melatih model Naive Bayes Classifier. Evaluasi kinerja model dilakukan menggunakan confusion matrix, yang menghasilkan akurasi sebesar 93,17% dan error rate sebesar 6,83%. Proses ini dilakukan terhadap dataset komentar YouTube yang telah diberi label melalui K-Means Clustering. Hasil klasifikasi menggunakan metode Naive Bayes menunjukan bahwa 3328 data komentar setuju dengan adanya naturalisasi pemain dan 256 data komentar tidak setuju.
Metode Latent Dirichlet Allocation Untuk Menentukan Topik Pada Review Drama Korea Alfun Roehatul Jannah; Kristi, Ria; Muhammad Habibi
INDONESIAN JOURNAL ON DATA SCIENCE Vol 2 No 1 (2024): Indonesian Journal on Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v2i1.1345

Abstract

The Hallyu Wave, involving the spread of South Korean culture and popular media, has rapidly grown over the past two decades. In addition to entertainment industries such as K-pop and K-drama, this phenomenon has also extended into the food and K-beauty sectors. Korean dramas, as the core of Hallyu, have become a global phenomenon with a continuously expanding fan base worldwide. A global survey in 2022 indicated that 36 percent of respondents in 26 countries considered Korean dramas very popular in their respective countries. In Indonesia, Korean films and dramas remain favorites, with 72 percent of streaming audiences choosing them on OTT services throughout 2022. Viu dominates as the most popular Korean drama streaming platform with 57 percent usage, followed by Netflix, Telegram, and WeTv. This research focuses on the analysis of Korean drama review data from 2015 to 2023 using the Latent Dirichlet Allocation (LDA) method. The goal is to provide a deep understanding of critical aspects such as acting, storyline, and cinematography. With LDA, this research aims to identify topics related to these elements, offering specific insights into audience preferences. From the conducted research, 10 ideal topics emerged out of 20 existing topics to ensure topic consistency using topic coherence. From the topic coherence results for these 20 topics, it can be concluded that the overall topic score for topic 10 is 0.527, providing ideal results for topic modeling in accordance with the rules.
ANALISIS PROYEKSI KEBUTUHAN TENAGA KERJA BERDASARKAN SKILLS YANG DIBUTUHKAN MENGGUNAKAN ALGORITMA NAIVE BAYES CLASSIFIER Nur Azizah Firdausa; Rifanny Br Girsang, Ribka; Oktaviana, Dela; Wahyuningsiam, Astr; Habibi, Muhammad
INDONESIAN JOURNAL ON DATA SCIENCE Vol 2 No 1 (2024): Indonesian Journal on Data Science
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat Universitas Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/ijds.v2i1.1346

Abstract

In August 2023, Indonesia faced an unemployment rate of 7.86 million people, although there is no denying that the percentage of unemployment has decreased from the previous year. The data is categorized into four groups, namely unemployment involves those who are looking for work, trying to set up a business having trouble landing a job, and even those who have worked but have not started. The Covid-19 pandemic changed the paradigm of work to remote, but the need for job information remains key. Labor demand projections provide long-term insights into promising sectors and fields, guiding job seekers to develop skills according to labor market trends. This research was conducted using naive bayes classification, which is a text classification method that relies on the likelihood of keywords to compare training and testing documents. This classification method is expected to help reduce unemployment rates and align individual skills with industry needs, contributing to education and training policies to make smart career decisions in the digital era.