Article Per Year (5 Year)
p-Index From 2020 - 2025
0.61
P-Index
This Author published in this journals
All Journal Jurnal Algoritma Jurnal Algoritma
Ajiz, Rafi Nurkholiq
Unknown Affiliation
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Analisis Sentimen Pengguna Twitter dalam Pemilihan Presiden (PILPRES) 2024 dengan Menggunakan Algoritma K-Means Amin, Abdusy Syakur; Kurniadi, Dede; Nurzaman, Muhammad Zein; Nurfadillah, Rifa Sri; Khoerunisa, Sarah; Khaerunisa, Nisrina; Ajiz, Rafi Nurkholiq; Jembar, Tegar Hanafi; Faisal, Ridwan Nur
Jurnal Algoritma Vol 21 No 1 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-1.1596

Abstract

One form of upholding democracy carried out by the Unitary State of the Republic of Indonesia is through holding presidential elections or often known as presidential elections. which is held every five years to elect the next President. Apart from that, in this digital era, people are increasingly actively using social media to convey their views, opinions and sentiments regarding the presidential election. Ahead of the 2024 presidential election, many groups such as political parties, success teams, buzzers and supporters are using social media as a campaign medium to increase the popularity and electability of their prospective candidates. One of the social media that is widely used in political party promotion media is Twitter. Which is used by people to post various comments that can be positive or negative regarding the election. Sometimes, people also express hoax opinions before or during the election. Considering that comments on Twitter are currently difficult to categorize as positive or negative, sentiment analysis is needed to understand public attitudes towards the presidential election. This research aims to evaluate text documents and determine whether the documents have a positive or negative sentiment orientation. Apart from that, the method used is K-Means to cluster the data. The results of this weighting are in the form of positive and negative sentiment. Data taken from Twitter regarding the 2024 presidential election (pilpres) totaling 1015 tweet data.
Analisis Sentimen Pengguna Twitter dalam Pemilihan Presiden (PILPRES) 2024 dengan Menggunakan Algoritma K-Means Amin, Abdusy Syakur; Kurniadi, Dede; Nurzaman, Muhammad Zein; Nurfadillah, Rifa Sri; Khoerunisa, Sarah; Khaerunisa, Nisrina; Ajiz, Rafi Nurkholiq; Jembar, Tegar Hanafi; Faisal, Ridwan Nur
Jurnal Algoritma Vol 21 No 1 (2024): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.21-1.1596

Abstract

One form of upholding democracy carried out by the Unitary State of the Republic of Indonesia is through holding presidential elections or often known as presidential elections. which is held every five years to elect the next President. Apart from that, in this digital era, people are increasingly actively using social media to convey their views, opinions and sentiments regarding the presidential election. Ahead of the 2024 presidential election, many groups such as political parties, success teams, buzzers and supporters are using social media as a campaign medium to increase the popularity and electability of their prospective candidates. One of the social media that is widely used in political party promotion media is Twitter. Which is used by people to post various comments that can be positive or negative regarding the election. Sometimes, people also express hoax opinions before or during the election. Considering that comments on Twitter are currently difficult to categorize as positive or negative, sentiment analysis is needed to understand public attitudes towards the presidential election. This research aims to evaluate text documents and determine whether the documents have a positive or negative sentiment orientation. Apart from that, the method used is K-Means to cluster the data. The results of this weighting are in the form of positive and negative sentiment. Data taken from Twitter regarding the 2024 presidential election (pilpres) totaling 1015 tweet data.
Klasifikasi Informasi Permintaan Bantuan Pada Saat Bencana Menggunakan Random Forest Dan Representasi Semantik Abstract Meaning Representation (AMR) Sutedi, Ade; Ajiz, Rafi Nurkholiq
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.2011

Abstract

Media sosial telah menjadi salah satu sumber utama dalam melaporkan peristiwa bencana alam, memungkinkan penyebaran informasi terkait bencana dengan cepat. Namun, informasi yang diunggah sering kali tidak terstruktur, dengan variasi dalam format dan konten, sehingga sulit untuk dianalisis dan dimanfaatkan secara efektif dalam situasi darurat. Permasalahan ini memerlukan solusi yang dapat mengolah informasi tersebut secara efisien. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi informasi bencana alam dari media sosial dengan memanfaatkan metode Abstract Meaning Representation (AMR) dan algoritma Random Forest. Metodologi yang diterapkan adalah Machine Learning Life Cycle (MLLC). Dataset yang digunakan terdiri dari 3.190 entri laporan bencana alam dari media sosial yang diproses dengan AMR untuk mengekstrak makna semantik dari teks. Algoritma Random Forest diterapkan untuk membangun model klasifikasi. Hasil evaluasi menggunakan Confusion Matrix menunjukkan model memiliki akurasi sebesar 86%, presisi 87%, recall 98%, dan F1-Score 92%. Berdasarkan hasil ini, model dapat membantu mempermudah klasifikasi informasi bencana alam, sehingga mendukung pengambilan keputusan secara cepat dan efektif dalam situasi darurat.
Co-Authors Abdusy Syakur Amin Ade Sutedi, Ade Dede Kurniadi Faisal, Ridwan Nur Jembar, Tegar Hanafi Khaerunisa, Nisrina Khoerunisa, Sarah Nurfadillah, Rifa Sri Nurzaman, Muhammad Zein