Garuda - Garba Rujukan Digital

Penerapan Algoritma Random Forest Untuk Analisis Sentimen Komentar Di YouTube Tentang Islamofobia Ibnu Afdhal; Rahmad Kurniawan; Iwan Iskandar; Roni Salambue; Elvia Budianita; Fadhilah Syafria
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 1 (2022): Februari 2022
Publisher : Program Studi Teknik Informatika, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i1.4004

Abstrak - Islamofobia adalah bentuk prasangka, intimidasi, kebencian dan ketakutan terhadap agama Islam dan orang Muslim. Stigma islamofobia muncul karena adanya suatu kejadian pengeboman atau teror lainnya yang dihubungkan dengan Islam. Komentar yang mengarah ke islamofobia banyak dijumpai pada media sosial youtube. Islamofobia di internet merupakan salah satu bentuk kekerasan verbal. Oleh karena itu, komentar pengguna terkait suatu kejadian pengeboman atau teror berpotensi untuk dianalisis sebagai bentuk kepedulian dalam mencegah kekerasan verbal. Tetapi analisis secara manual sulit dilakukan dan memerlukan waktu yang lama. Algoritma pada pembelajaran mesin dapat digunakan untuk melakukan analisa sentimen dengan cepat. Algoritma yang digunakan pada penelitian ini adalah random forest. Berdasarkan studi pustaka, algoritma random forest dapat menghasilkan ketepatan yang tinggi. Penelitian ini menggunakan 1000 data komentar di youtube berbahasa Indonesia terkait video yang menampilkan suatu kejadian pengeboman atau teror. Berdasarkan hasil analisis, terdapat 631 komentar positif dan 369 komentar negatif atau mengandung islamofobia. Berdasarkan eksperimen, algoritma random forest menghasilkan akurasi mencapai 79%. Algoritma random forest dianggap baik dalam melakukan klasifikasi sentimen dengan cepat.Kata kunci: analisis sentimen, islamofobia, random forest, youtube Abstract - Islamophobia is a form of prejudice, intimidation, hatred, and fear of Islam and Muslims. The stigma of Islamophobia arises because of bombing or other terror associated with Islam. Comments that lead to Islamophobia are often found on social media youtube. Islamophobia on the internet is a form of verbal violence. Therefore, user comments related to a bombing or terror incident have the potential to be analyzed as a form of concern in preventing verbal violence. However, manual analysis is difficult and takes a long time. Algorithms in machine learning can be used to perform sentiment analysis quickly. The algorithm used in this study is a random forest. The random forest algorithm can produce high accuracy based on the literature study. This study obtained 1000 comments data on youtube in Indonesian related to videos showing a bombing or terror incident. Based on the analysis results, there were 631 positive comments and 369 islamophobia i.e., negative comments. Based on experiments, the random forest algorithm produces an accuracy of 79%. The random forest algorithm is considered good in doing sentiment classification quickly.Keywords—islamophobia, random forest, sentiment analysis, Youtube

PENGKLASTERAN RISIKO COVID-19 DI RIAU MENGGUNAKAN TEKNIK ONE HOT ENCODING DAN ALGORITMA K-MEANS CLUSTERING Silvi Ana; Rahmad Kurniawan; Alwis Nazir
Jurnal informasi dan komputer Vol 10 No 1 (2022): Jurnal Sistem Informasi dan Komputer yang terbit pada tahun 2022 pada bulan 04 (
Publisher : STMIK Dian Cipta Cendikia Kotabumi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35959/jik.v10i1.291

Coronavirus disease 2019 (COVID-19) merupakan jenis penyakit baru yang diketahui menjangkiti manusia pada Desember 2019. Kasus COVID-19 telah menyebar di seluruh penjuru dunia termasuk di Indonesia. Salah satu provinsi dengan jumlah kasus COVID-19 yang cukup tinggi adalah Provinsi Riau. Tindakan mitigasi yang tepat diperlukan untuk mencegah wabah COVID-19. Berdasarkan studi pustaka, COVID-19 mewabah berdasarkan jarak terdekat. Ahli epidemiologi juga telah menggunakan metode clustering untuk mengelompokkan daerah-daerah yang terkena Pandemi COVID-19. Oleh karena itu, penelitian ini menggunakan teknik one hot encoding dan algoritma k-means clustering untuk mengelompokkan daerah yang memiliki karakteristik data yang mirip. Penelitian ini menggunakan data 12 Kabupaten di Riau dengan tujuh fitur. Berdasarkan eksperimen, dihasilkan tiga klaster yaitu C1 (Pekanbaru, Kampar), C2 (Siak, Bengkalis, Rokan Hulu, Kuantan Singingi), dan C3 (Dumai, Indragiri Hilir, Indragiri Hulu, Pelalawan, Rokan Hilir, Meranti). Hasil klaster tersebut telah diuji dengan skor silhouette sebesar 0,6. Dengan demikian, dapat disimpulkan bahwa teknik one hot encoding dan algoritma k-means clustering berpotensi digunakan untuk mengelompokkan wilayah pandemi COVID-19 berdasarkan karakteristik data yang mirip.

Penerapan Metode SMART untuk Menentukan Kelayakan Perpustakaan Sekolah - Sukamto; Rahmad Kurniawan; Avisha Delinda Jukris
Techno.Com Vol 22, No 2 (2023): Mei 2023
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33633/tc.v22i2.7531

Perpustakaan sekolah harus diakreditasi dengan tujuan untuk meningkatkan kualitas perpustakaan. Dinas Perpustakaan dan Kearsipan Kota Pekanbaru (DISPUSIP) dalam menentukan suatu perpustakaan sekolah yang layak untuk diakreditasi masih dilakukan secara manual. Untuk itu diperlukan suatu sistem pendukung keputusan (SPK). Penelitian ini menggunakan metode SMART. Alternatif yang digunakan adalah sembilan (9) sekolah jenjang SMP baik negeri maupun swasta. Kriteria yang digunakan mengacu pada instrument akreditasi perpustakaan sekolah yang dikeluarkan oleh Perpustakaan Nasional (Perpusnas) terdiri dari enam (6) kriteria yaitu koleksi, sarana dan prasarana perpustakaan, pelayanan perpustakaan, tenaga perpustakaan, penyelenggaraan dan pengelolaan perpustakaan, serta penguat. Hasil penelitian yang diperoleh untuk perpustakaan SMP adalah Sek 4, Sek 5 dan Sek 3 yang layak untuk diakreditasi

Klasifikasi Kebakaran Hutan Riau Menggunakan Random Forest dan Visualisasi Citra Sentinel-2 Ahmad Efendi; Iwan Iskandar; Rahmad Kurniawan; Muhammad Affandes
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 3 (2023): Desember 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i3.1521

In September 2019, Riau was severely affected by hazardous haze, impacting the health of the population and disrupting the activities of approximately 6.5 million people. This situation necessitated swift and accurate actions for the mitigation and anticipation of forest and land fires. This research aims to classify forest fires in Riau using Machine Learning algorithms, specifically Random Forests. However, a comprehensive understanding of forest fires requires the visualization of Sentinel-2 satellite imagery using the Normalized Burn Ratio (NBR) index. Sentinel-2 imagery recreates a pivotal role in identifying burnt areas, measuring fire intensity, and assessing environmental impacts. Weather data spanning from January 2015 to September 2019, totaling 1733 data points have been utilized in this study. Experimental results demonstrate that the Random Forest algorithm achieved the highest accuracy of 71% with an 90% training data allocation. Meanwhile, Sentinel-2 imagery can visualize burnt areas with an overall accuracy of 94% and a kappa coefficient of 0.92. This study offers an integrated approach to addressing forest fires in Riau, resulting in improved predictions and a deeper understanding of forest fire disasters. In the context of disaster mitigation, the combination of Machine Learning and Sentinel-2 imagery visualization holds significant potential for providing critical information to stakeholders and authorities

Penerapan Algoritma Random Forest Untuk Analisis Sentimen Komentar Di YouTube Tentang Islamofobia Ibnu Afdhal; Rahmad Kurniawan; Iwan Iskandar; Roni Salambue; Elvia Budianita; Fadhilah Syafria
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 1 (2022): Februari 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i1.4004

Abstrak - Islamofobia adalah bentuk prasangka, intimidasi, kebencian dan ketakutan terhadap agama Islam dan orang Muslim. Stigma islamofobia muncul karena adanya suatu kejadian pengeboman atau teror lainnya yang dihubungkan dengan Islam. Komentar yang mengarah ke islamofobia banyak dijumpai pada media sosial youtube. Islamofobia di internet merupakan salah satu bentuk kekerasan verbal. Oleh karena itu, komentar pengguna terkait suatu kejadian pengeboman atau teror berpotensi untuk dianalisis sebagai bentuk kepedulian dalam mencegah kekerasan verbal. Tetapi analisis secara manual sulit dilakukan dan memerlukan waktu yang lama. Algoritma pada pembelajaran mesin dapat digunakan untuk melakukan analisa sentimen dengan cepat. Algoritma yang digunakan pada penelitian ini adalah random forest. Berdasarkan studi pustaka, algoritma random forest dapat menghasilkan ketepatan yang tinggi. Penelitian ini menggunakan 1000 data komentar di youtube berbahasa Indonesia terkait video yang menampilkan suatu kejadian pengeboman atau teror. Berdasarkan hasil analisis, terdapat 631 komentar positif dan 369 komentar negatif atau mengandung islamofobia. Berdasarkan eksperimen, algoritma random forest menghasilkan akurasi mencapai 79%. Algoritma random forest dianggap baik dalam melakukan klasifikasi sentimen dengan cepat.Kata kunci: analisis sentimen, islamofobia, random forest, youtube Abstract - Islamophobia is a form of prejudice, intimidation, hatred, and fear of Islam and Muslims. The stigma of Islamophobia arises because of bombing or other terror associated with Islam. Comments that lead to Islamophobia are often found on social media youtube. Islamophobia on the internet is a form of verbal violence. Therefore, user comments related to a bombing or terror incident have the potential to be analyzed as a form of concern in preventing verbal violence. However, manual analysis is difficult and takes a long time. Algorithms in machine learning can be used to perform sentiment analysis quickly. The algorithm used in this study is a random forest. The random forest algorithm can produce high accuracy based on the literature study. This study obtained 1000 comments data on youtube in Indonesian related to videos showing a bombing or terror incident. Based on the analysis results, there were 631 positive comments and 369 islamophobia i.e., negative comments. Based on experiments, the random forest algorithm produces an accuracy of 79%. The random forest algorithm is considered good in doing sentiment classification quickly.Keywords—islamophobia, random forest, sentiment analysis, Youtube

Analisis Sentimen Komentar Di YouTube Tentang Ceramah Ustadz Abdul Somad Menggunakan Algoritma Naïve Bayes Habibi Al Rasyid Harpizon; Rahmad Kurniawan; Iwan Iskandar; Roni Salambue; Elvia Budianita; Fadhilah Syafria
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 1 (2022): Februari 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i1.4008

Abstrak - Sosial media tidak hanya digunakan oleh masyarakat Indonesia untuk hiburan, tetapi juga sebagai media edukasi. Youtube merupakan salah satu media sosial yang terkenal di Indonesia dengan 93,8% pengguna. Youtube juga dimanfaatkan sebagai media Dakwah seperti yang dilakukan oleh Ustadz Abdul Somad. Ustadz Abdul Somad merupakan ulama yang berpengaruh di Indonesia. Beliau sering mengunggah video yang membahas berbagai jenis persoalan agama khususnya pada bidang hadist dan fiqih. Pengguna Youtube dapat memberikan feedback berupa like, dislike dan komentar terhadap video yang ditayangkan. Feedback diperlukan oleh pembuat konten di Youtube untuk melihat tanggapan pengguna. Analisa secara manual sulit dilakukan karena jumlah data yang besar. Oleh karena itu, penelitian ini bertujuan untuk menganalisis sentimen masyarakat terhadap Ustadz Abdul Somad melalui komentar youtube menggunakan algoritma Naïve Bayes. Penelitian ini menggunakan 1000 komentar dari 10 video yang ada di Youtube mengenai Ustad Abdul Somad. Naïve Bayes merupakan algoritma yang sederhana, namun memiliki akurasi yang tinggi dan dapat digunakan pada data yang sedikit. Berdasarkan hasil penelitian, didapatkan sebanyak 67% berkomentar positif, 27% berkomentar netral dan 6% berkomentar negatif. Berdasarkan pengujian didapatkan akurasi sebesar 87%, presisi 91% dan recall 97%. Berdasarkan pengujian tersebut dapat disimpulkan bahwa penelitian ini dapat digunakan untuk hasil sentimen dengan cepat di Youtube.Kata kunci: Analisis Sentimen, Naïve Bayes, Ustadz Abdul Somad, Youtube Abstract - Indonesian people have been used Youtube for entertainment and as an education. As Indonesia's most popular social media, Youtube has 93.8% users. YouTube is also used as a medium of Da'wah, like Ustadz Abdul Somad. Ustadz Abdul Somad is an influential Preacher in Indonesia. He often uploads videos that lecture various types of religious issues, especially in the fields of hadith and fiqh. YouTube users can provide feedback in the form of likes, dislikes, and comments on videos that are shown. Creators need feedback on YouTube to see user feedback. Manual analysis is complicated because of the large amount of data. Therefore, this study aimed to analyze public sentiment towards Ustadz Abdul Somad through YouTube comments using the Naïve Bayes algorithm. This study obtained 1000 comments from 10 videos about Ustad Abdul Somad. Naïve Bayes is a simple algorithm with high accuracy and can be used on small data. Based on the results, it was found that 67% commented positively, 27% commented neutrally, and 6% commented negatively. Based on the experimental testing, the accuracy is 87%, precision is 91%, and recall is 97%. Based on these tests, it can be concluded that this research can be used for quick sentiment results on YouTube.Keywords: Sentiment Analysis, Naïve Bayes, Ustadz Abdul Somad, Youtube

Sentiment analysis of student evaluation feedback using transformer-based language models Daqiqil ID, Ibnu; Saputra, Hendy; Syamsudhuha, Syamsudhuha; Kurniawan, Rahmad; Andriyani, Yanti
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 2: November 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i2.pp1127-1139

This paper proposes an approach to sentiment analysis of student evaluation feedback using transformer-based language models. The primary objective of this study is to conduct an in-depth analysis of sentiment expressed in student evaluation feedback, with a focus on introducing contextual understanding into the sentiment classification process. In this research, four different variants of transformer language models were assessed, namely multilingual bidirectional encoder representations from transformers (MBERT), IndoBERT, RoBERTa Indonesia, and generative pre-trained transformer (GPT-2 Indonesia). Additionally, we also compared the performance of transformer models with two traditional models, namely support vector machine (SVM) and Naive Bayes (NB). The evaluation was conducted using feedback data collected from the Evaluasi Dosen oleh Mahasiswa (EDOM) system at Riau University, which had been categorized as either positive or negative. The outcomes indicate that IndoBERT base uncased exhibits the highest performance, with precision, accuracy, and recall values of 0.858, 0.929, and 0.911, respectively. This observation highlights the effectiveness of transformer-based language models in sentiment analysis of student evaluation feedback and provides insights for improving educational assessment practices.

Risk Management Analysis of Information Security in an Academic Information System at a Public University in Indonesia: Implementation of ISO/IEC 27005:2018 and ISO/IEC 27001:2013 Security Controls Meitarice, Sonya; Febyana, Lidya; Fitriansyah, Aidil; Kurniawan, Rahmad; Nugroho, Riki Ario
Journal of Information Technology and Cyber Security Vol. 2 No. 2 (2024): July
Publisher : Department of Information Systems and Technology, Faculty of Intelligent Electrical and Informatics Technology, Universitas 17 Agustus 1945 Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30996/jitcs.12099

An online academic information system is potentially exposed to various threats from internal and external sources, which may compromise the institution's objectives if not managed effectively and appropriately. Academic portals often experience issues such as server downtime and unauthorised access attempts. However, there is no specific documentation dedicated to managing these issues. This study aims to analyze risk management in information security for the academic portal of Universitas Riau, Indonesia. The study employs the International Organization for Standardization (ISO)/International Electrotechnical Commission (IEC) 27005:2018 standard and ISO/IEC 27001:2013 security controls, following four key stages: context establishment, risk assessment, risk treatment, and recommendations. The findings identify eight categories of information system assets, 30 identified threats, and 43 vulnerabilities, including two high-risk categories, 19 medium-risk categories, and 22 low-risk categories. Of the 43 vulnerabilities, 21 risks required risk modification, four required risk avoidance, and four required risk sharing. Fourteen risks, which can be managed through risk retention (acceptance of risk), fall under the category of risk acceptance. Furthermore, ISO/IEC 27001 suggests that implementing control recommendations can minimize and effectively address these risks. Nevertheless, this study focuses primarily on information security risks and does not extensively cover related areas such as data privacy, regulatory compliance, or operational risks. Future research can explore the effectiveness of training programs and awareness campaigns in reducing human-related risks, such as phishing and social engineering attacks.

Interactive Geographic Visualization and Unsupervised Learning for Optimal Assignment of Preachers to Appropriate Congregations Rahmad Kurniawan; Ibnu Daqiqil ID; Abdul Somad Batubara; Fitra Lestari; Arisman Adnan; Fatayat Fatayat; Ilyas Husti
Journal of Applied Engineering and Technological Science (JAETS) Vol. 6 No. 1 (2024): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v6i1.5760

Riau Province has a population of 6,642,874 and a diverse geography, which poses significant challenges in optimizing Islamic preaching activities. Traditional assignment methods often lead to inefficiencies due to misalignment between the preacher’s expertise and congregational needs, as well as logistical issues. This study integrates K-Means clustering and DBSCAN algorithms with interactive geographic visualization to optimize the assignment of preachers to mosques. We collected 435 data points, including 185 mosques and 250 preachers. K-Means was evaluated using the Elbow Method and Silhouette Score, identifying 10 clusters as optimal with a Silhouette Score of 0.435654. However, K-Means does not handle outliers effectively, as indicated by zero outliers in all configurations. DBSCAN was tested with various epsilon (eps) and minimum sample values. The optimal configuration with eps of 1.5 and 5 minimum samples resulted in 10 clusters with a Silhouette Score of 0.381108 and 60 outliers. DBSCAN effectively manages outliers and varying densities. Although K-Means is advantageous for its simplicity and higher Silhouette Scores, it is unable to handle outliers effectively. DBSCAN provides robust clustering for noisy data. Therefore, it can be concluded that hybridizing unsupervised learning algorithms with geographic visualization can potentially improve the effectiveness of preaching activities in Riau Province and enhance preacher assignment.

Title

Found 19 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 19 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 19 Documents
Search