Muhammad Nur Akbar
Universitas Islam Negeri Alauddin Makassar

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

ANALISIS CLUSTERING TEKS TANGGAPAN MASYARAKAT DI TWITTER TERHADAP PEMBATASAN SOSIAL BERSKALA BESAR MENGGUNAKAN ALGORITMA K-MEANS Muhammad Nur Akbar; Darmatasia Darmatasia; Mustikasari Mustikasari; Muh Syahwal
Jurnal INSYPRO (Information System and Processing) Vol 6 No 1 (2021)
Publisher : Prodi Sistem Informasi UIN Alauddin

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (609.636 KB) | DOI: 10.24252/insypro.v6i1.23325

Abstract

Virus corona (COVID-19) ditetapkan sebagai pandemi oleh WHO (World Health Organization atau Badan Kesehatan Dunia) karena penyebarannya yang terus meningkat dan telah mencapai sebagian besar negara di dunia, termasuk Indonesia. Setiap negara dituntut dapat lebih agresif dalam mengambil tindakan pencegahan dan perawatan. Pemerintah Indonesia sendiri mengeluarkan kebijakan berupa wajib masker, jam malam, serta PSBB (Pembatasan Sosial Berskala Besar) guna menekan laju menyebaran COVID-19.  Namun kebijakan tersebut menuai tanggapan  pro dan kontra dari masyarakat khususnya melalui media sosial, di satu sisi PSBB dianggap mampu menekan laju penyebaran COVID-19 namun di sisi lain PSBB dianggap akan memperburuk kondisi perekonomian masyarakat, khususnya golongan menengah bawah. Penelitian ini bertujuan untuk mengelompokkan tanggapan masyarakat mengenai PSBB di twitter ke dalam beberapa cluster, tanggapan yang berada dalam satu cluster yang sama dianggap memiliki topik atau karakteristik pembahasan yang serupa dan sebaliknya, sehingga dapat memberi insight tambahan pada pihak pemerintah dalam mengevaluasi kebijakannya. Algoritma K-Means digunakan untuk mengelompokkan tanggapan yang memiliki kesamaan karakteristik sebab terbukti memiliki tingkat akurasi yang tinggi dengan waktu eksekusi yang relatif cepat karena bersifat linear. Penelitian ini menghasilkan 4 cluster berbeda dengan mengunakan metode Elbow dalam penentuan jumlah K pada algoritma K-Means dan nilai SSE (Sum of Square Error) sebagai parameter evaluasinya.   
Analisis Sentimen Pengguna Indihome dengan Metode Klasifikasi Support Vector Machine (SVM) Muhammad Nur Akbar; Nur Annisa Safitri Yusuf; Nasrullah Nasrullah; Mubarak Mubarak
Journal Software, Hardware and Information Technology Vol 2 No 1 (2022)
Publisher : Jurusan Sistem Informasi Universitas Islam Negeri Alauddin Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/shift.v2i1.18

Abstract

Indonesia Digital Home (IndiHome) is a communication service provider from PT Telekomunikasi Indonesia (Telkom) that provides several communication and data service packages such as internet, home telephone and cable television (Usee TV & IP TV) which implements copper and fiber pptic cable services. Currently, IndiHome is implementing a 100% fiber service replacement for all customers in order to produce high data speeds and more reliable services. However, the fact is that fiber optic services often receive complaints from customers due to weather and other factors. It was recorded that in 2020 internet users in Indonesia reached 196.7 million people or 73.7% million of the population and around 51.2% were social media users (Kompas.com, 2020). One of the social media with 6.43 million active users is Twitter. Twitter then became a medium for channeling opinions regarding a service, including the services provided by Indihome. Based on this, a method is needed, namely sentiment analysis to understand whether the opinion is negative or positive. The Support Vector Machine (SVM) is used to create a classification model for sentiment analysis of IndiHome service users' opinions on Twitter with an accuracy of 91.3%.
Penambangan Pengklasifiksi Fuzzy dengan Multiobjective Evolutionary Fuzzy Classifier Nur Salman; Mustikasari Mustikasari; Muhammad Nur Akbar
Journal Software, Hardware and Information Technology Vol 2 No 1 (2022)
Publisher : Jurusan Sistem Informasi Universitas Islam Negeri Alauddin Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/shift.v2i1.24

Abstract

Classification is one of the key issues in the field of data mining and knowledge discovery. This paper implements a method of constructing a fuzzy rule mining classifier, which is extended in the context of classification. There are three stages of this approach: fuzzy rule set extraction, second; a linguistic labeling process that assigns a linguistic label to each fuzzy set. Owing to many attributes in the database, the feature selection process is also carried out, reducing the complexity to build the final classifier. Third: incorporate strategies to avoid rule redundancy and conflict into process mining. We applied the application Multiobjective Evolutionary Fuzzy Classifier (MOFC), which produced a classifier with satisfactory classification accuracy compared to other classifiers such as C4.5. In addition, in terms of classification based on association rules, MOFC can filter the large of rules and be proven to be able to build compact fuzzy models while maintaining a very good level of accuracy and producing a much smaller set of rules. We examine the performance of fuzzy rule classifiers through computational experiments on three benchmark data sets in the UCI machine learning repository.
KLASIFIKASI BIBLIOGRAFI OTOMATIS MENGGUNAKAN C4.5 DAN INFORMATION GAIN MUHAMMAD NUR AKBAR
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 6 No 1 (2021)
Publisher : Department of informatics engineering Faculty of Science and Technology Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (426.099 KB) | DOI: 10.24252/instek.v6i1.18636

Abstract

Permasalahan yang dibahas pada penelitian ini mengenai klasifikasi bibliografi. Klasifikasi dilakukan dengan memproses data-data dari berbagai sumber referensi yang diberikan. Metode yang diterapkan dalam pengklasifikasian adalah C4.5 dengan sebelumnya dilakukan beberapa tahap preprocessing. C4.5 yang digunakan untuk proses text mining karena memiliki akurasi dan kecepatan yang sangat tinggi dengan algoritma yang sederhana. Digunakan pula Information Gain untuk evaluasi atribut yang dipilih dalam mengklasifikasikan dokumen.Kata Kunci: Text mining, C.45, bibliography, feature selection, Information Gain  
Analisis Sentimen Terhadap Jasa Ekspedisi Pos Indonesia Pada Sosial Media Twitter Menggunakan Naïve Bayes Classifier Muhammad Nur Akbar; Darmatasia Darmatasia; Yulia Ardana
Journal Software, Hardware and Information Technology Vol 2 No 2 (2022)
Publisher : Jurusan Sistem Informasi Universitas Islam Negeri Alauddin Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/shift.v2i2.34

Abstract

Nowdays, the rapid growth of information technology positively impacts companies engaged in industry, sales, and services, especially e-commerce. The increase in the number of transactions in various e-commerce impacts the increase in the use of expedition services. Pos Indonesia is the oldest expedition service provider in Indonesia and is required to be able to innovate in providing the best service for its customers. The importance of customers for a company depends on how the company builds customer relationships. A strong company will have good customer relations. Many customers have expressed their opinions regarding Pos Indonesia through Twitter. In this study, text mining techniques are used, namely sentiment analysis which helps analyze opinions, sentiments, evaluations, assessments, attitudes, and public emotions towards Pos Indonesia services. Naïve Bayes Classifier was chosen because it is simple, fast, and has high accuracy. The Naïve Bayes Classifier has successfully classified positive and negative sentiments on 100 tweets from Pos Indonesia customers with an accuracy of 87%.