Article Per Year (5 Year)
p-Index From 2021 - 2026
1.235
P-Index
This Author published in this journals
All Journal Khazanah Informatika: Jurnal Ilmu Komputer dan Informatika JURIKOM (Jurnal Riset Komputer) JURNAL MAHAJANA INFORMASI Journal of Robotics and Control (JRC) Abdimas: Papua Journal Of Community Service Jurnal Pengabdian Nasional (JPN) Indonesia IJMST
Murni
Fakultas Teknik, Universitas Muhammadiyah Sorong, Papua Barat Daya, 98416, Indonesia
Aerospace Engineering Humanities Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mechanical Engineering Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Analisis Sentimen HateSpeech pada Pengguna Layanan Twitter dengan Metode Naïve Bayes Classifier (NBC) Murni Murni; Imam Riadi; Abdul Fadlil
JURIKOM (Jurnal Riset Komputer) Vol 10, No 2 (2023): April 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v10i2.5984

Abstract

In January 2023, Twitter users experienced a significant increase of 27.4% compared to the previous year. The social media platform Twitter is commonly used to share various types of information. One type of information frequently shared by users is Hate Speech. Hate Speech involves the dissemination of messages that nurture feelings of hatred and hostility towards specific individuals or groups, including ethnicity, religion, race, and other categories. Forms of Hate Speech encompass insults, defamation, blasphemy, provocation, incitement, and the spread of fake news. In order to address the potential for division and threats to Indonesia's unity, sentiment analysis capable of categorizing tweets as Hate Speech or Non-Hate Speech is necessary. This research aims to conduct sentiment analysis on Hate Speech tweets posted by Twitter users using the Naïve Bayes Classifier method. The dataset consists of 5000 samples processed using the Python programming language. Data processing stages involve preprocessing (including case folding, tokenization, stopword removal, normalization, and stemming), labeling, and assigning word weights (Term Weighting) using the Term Frequency (TF) and Inverse Document Frequency (IDF) methods. The data is then divided into training and testing sets, with three different data splits: 70% training and 30% testing, 30% training and 70% testing, and 50% training and 50% testing. Evaluation using the Confusion Matrix yields the highest accuracy of 81%, precision of 81%, recall of 100%, and F1-Score of 90% in the 70% training and 30% testing data split.
Identifying Hate Speech in Tweets with Sentiment Analysis on Indonesian Twitter Utilizing Support Vector Machine Algorithm Imam Riadi; Abdul Fadlil; Murni Murni
Khazanah Informatika Vol. 9 No. 2 October 2023
Publisher : Department of Informatics, Universitas Muhammadiyah Surakarta, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23917/khif.v9i2.22470

Abstract

Twitter had 24 million users in Indonesia at the beginning of 2023. Despite having fewer users than other platforms, its fast and instant nature makes Twitter a significant source of information dissemination. Tweets shared on Twitter offer various advantages. However, it also has negative consequences, including the dissemination of fake news, instances of cyberbullying, and the expression of hate speech. Specifically, hate speech employs offensive language to discriminate against an individual or group based on race, ethnicity, nationality, religion, gender, sexual orientation, or other personal attributes, leading to discord. Such behavior comes under the jurisdiction of various legal statutes, including the Constitution, the Criminal Code, and the ITE Law. The primary objective of this research is to categorize tweets shared on Twitter into hate speech and non-hate speech sentiments, utilizing a Support Vector Machine (SVM) algorithm based on a dataset of 5,000 tweets. This research involved data preprocessing, labeling, feature extraction using TF-IDF, model training (80%), and testing (20%). The final stage includes enhancing SVM parameters through GridSearch and cross-validation methods (GridSearchCV), followed by analysis using a Confusion Matrix with the Matplotlib Library. Radial Basis Function (RBF) kernels, defined by parameters C=10 and gamma=0.1, exhibited the highest performance among SVM models, boasting an 84% accuracy. The RBF kernel also attained 85% precision, 97% recall, and a 91% F1-score for hate speech identification. In conclusion, the evaluation of SVM kernel performance highlights the superiority of RBF kernels in achieving the highest accuracy, complemented by nuanced insights into hate speech precision, recall, and F1-score values across various kernel types.
Analysis and Performance Comparison of Fuzzy Inference Systems in Handling Uncertainty: A Review Furizal, Furizal; Ma'arif, Alfian; Wijaya, Setiawan Ardi; Murni, Murni; Suwarno, Iswanto
Journal of Robotics and Control (JRC) Vol 5, No 4 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i4.22123

Abstract

Uncertainty is an inevitable characteristic in human life and systems, posing challenges in decision-making and data analysis. Fuzzy theory emerges to address this uncertainty by describing variables with vague or uncertain values, one of which is the Fuzzy Inference System (FIS). This research analyzes and compares the performance of FIS from previous studies as a solution to manage uncertainty. FIS allows for flexible and responsive representations of truth levels using human-like linguistic rules. Common FIS methods include FIS-M, FIS-T, and FIS-S, each with different inference and defuzzification approaches. The findings of this research review, referencing previous studies, indicate that the application of FIS in various contexts such as prediction, medical diagnosis, and financial decision-making, yields very high accuracy levels up to 99%. However, accuracy comparisons show variations, with FIS-M tending to achieve more stable accuracy based on the referenced studies. The accuracy difference among FIS-M studies is not significantly different, only around 7.55%. Meanwhile, FIS-S has a wider accuracy range, from 81.48% to 99% (17.52%). FIS-S performs best if it can determine influencing factors well, such as determining constant values in its fuzzy rules. Additionally, the performance comparison of FIS can also be influenced by other factors such as data complexity, variables, domain, membership functions (curves), fuzzy rules, and defuzzification methods used in the study. Therefore, it is important to consider these factors and select the most suitable FIS method to manage uncertainty in the given situation.
Pengenalan Game Edukasi Flora dan Fauna untuk Siswa SD Inpres 4 Arborek Raja Ampat Tella, Fitriyani; Jundullah, Muhammad; Murni; Nurdjan, Nirwana; Hasa, Muh. Fadli; Ghiraldy
Jurnal Pengabdian Nasional (JPN) Indonesia Vol. 6 No. 1 (2025): Januari
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Indonesia Banda Aceh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35870/jpni.v6i1.1305

Abstract

Education in remote areas often encounters challenges such as inadequate infrastructure and limited access to technology, as seen at SD Inpres 4 Arborek, Raja Ampat, West Papua. To address these issues, a technology-based learning medium emphasizing Papua's biodiversity was developed. This interactive digital educational game includes features like a flora and fauna encyclopedia, quizzes, and puzzles designed to enhance students' comprehension of local natural resources. A community service activity conducted on August 21, 2024, engaged 38 students from grades 1 to 6, accompanied by two teachers and the vice principal. The activity employed direct student training and demonstrations to illustrate the game's potential as a learning tool. Students were encouraged to explore the game independently, while teachers observed its integration into daily learning routines. The results demonstrated the effectiveness of this educational medium in enhancing student motivation, engagement, and understanding. The integration of local content within the game also reinforced students' connection to their environment, cultivated cultural pride, and heightened conservation awareness. Challenges with younger students' adaptation to digital tools were mitigated through proper guidance. Questionnaire feedback indicated strong acceptance of the game as a supplementary learning resource and highlighted its potential as a model for implementing educational technology in other remote regions.
Diabetes Mellitus Disease Analysis using Support Vector Machines and K-Nearest Neighbor Methods Nusantara Habibi, Ahmad Rizky; Sufiyandi, Ilham; Murni, Murni; Jayed, A K M; Nakib, Arman Mohammad; Syukur, Abdul; Furizal, Furizal
Indonesian Journal of Modern Science and Technology Vol. 1 No. 1 (2025): January
Publisher : CV. Abhinaya Indo Group

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.64021/ijmst.1.1.22-27.2025

Abstract

Diabetes Mellitus (DM) is a chronic disease characterized by high blood sugar levels and can cause various serious complications if not treated properly. This study aims to analyze the effectiveness of Support Vector Machines (SVM) and K-Nearest Neighbor (KNN) methods in classifying diabetes mellitus patient data. The methodology used includes collecting diabetes datasets, preprocessing data, and applying SVM and KNN algorithms to perform classification. The performance of both methods is analyzed using evaluation metrics such as accuracy, precision, recall, and F1-score. The experimental results show that the SVM method provides more optimal performance in classifying diabetes data compared to KNN, with higher accuracy and lower error rate. This finding indicates that SVM is more suitable for early detection of diabetes mellitus in the dataset used in this study.
Penerapan AI Untuk Meningkatkan Kualitas Pendidikan Di SMP Negerti 3 Kota Sorong Teguh Hidayat Iskandar Alam; Murni; Fitriyani Tella; Irman Amri
Abdimas: Papua Journal of Community Service Vol. 7 No. 2 (2025): Juli
Publisher : Lembaga Pengembangan dan Pengabdian Masyarakat Universitas Muhammadiyah Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33506/pjcs.v7i2.4707

Abstract

The rapid advancement of digital technology has necessitated artificial intelligence (AI) literacy in the education sector. Unfortunately, the understanding of AI among teachers and students—particularly in underdeveloped regions like Sorong City—remains limited. This community service activity aimed to enhance participants’ comprehension, technical skills, and ethical awareness in AI utilization at SMP Negeri 3 Kota Sorong. The methods involved interactive lectures, hands-on training, group discussions, and formative evaluations through pre-tests and post-tests. The results demonstrated significant improvements in four key indicators: understanding of AI concepts, skills in using AI-based applications, digital ethics awareness, and interest in AI-related careers. The average participant scores increased by over 60%. The program successfully fostered a participatory and inclusive learning environment and cultivated interest in the educational use of technology. This training is recommended for broader implementation to accelerate digital literacy equity across educational institutions.
PERBANDINGAN ALGORITMA NAÏVE BAYES DAN LONG SHORT-TERM MEMORY DALAM KLASIFIKASI KUALITAS SUSU Fajar Rahardika Bahari Putra; Murni; Muhammad Surahmanto; Rezki; Dimas Adi Suseno
Jurnal Mahajana Informasi Vol 10 No 2 (2025): JURNAL MAHAJANA INFORMASI
Publisher : Universitas Sari Mutiara Indonesia Medan

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

Abstract

Latarbelakang: Kualitas susu merupakan aspek penting dalam industri pangan karena secara langsung berkaitan dengan keamanan konsumsi dan kesehatan masyarakat. Pengujian kualitas susu konvensional memiliki keterbatasan dalam efisiensi dan objektivitas, sehingga memerlukan pendekatan berbasis data untuk mendukung proses klasifikasi kualitas susu. Tujuan: Penelitian ini difokuskan pada perbandingan hasil klasifikasi antara algoritma Naïve Bayes dan Long Short-Term Memory (LSTM) pada data kualitas susu. Dataset dalam penelitian ini berupa data sekunder yang diambil melalui platform Kaggle, terdiri dari 844 data dengan tiga kelas kualitas, yaitu Low, Medium, dan High. Semua data digunakan sebagai populasi penelitian, dengan pembagian data pelatihan dan data uji, di mana 212 dataset digunakan sebagai data uji. Metode penelitian yang diterapkan adalah pendekatan eksperimental dengan simulation-based experiment, menggunakan dataset yang sama pada kedua algoritma. Penilaian performa model dilakukan dengan memanfaatkan metrik accuracy, Confusion matrix, Hasil: Berdasarkan hasil pengujian, algoritma Naïve Bayes mencapai tingkat accuracy sebesar 85%, lebih tinggi dibandingkan Long Short-Term Memory (LSTM) yang memperoleh 75%. Analisis per kelas menunjukkan bahwa Naïve Bayes lebih efektif dalam mengidentifikasi kelas Low dan Medium, sementara LSTM cenderung menghasilkan nilai recall yang lebih baik pada kelas Medium, namun menunjukkan penurunan kemampuan klasifikasi pada kelas Low dan High. Kesimpulan: Berdasarkan hasil tersebut, penelitian ini kemudian menegaskan bahwa pemilihan algoritma klasifikasi perlu disesuaikan dengan karakteristik dataset untuk mendapatkan hasil yang optimal.precision, recall, dan F1-score.
Co-Authors Abdul Fadlil Abdul Fadlil Abdul Syukur Alfian Ma’arif Amri, Irman Dimas Adi Suseno Fajar Rahardika Bahari Putra Fitriyani Tella Furizal, Furizal Ghiraldy Imam Riadi Imam Riadi Jayed, A K M Muh. Fadli Hasa Muhammad Jundullah Muhammad Surahmanto Nakib, Arman Mohammad Nurdjan, Nirwana Nusantara Habibi, Ahmad Rizky Rezki Sufiyandi, Ilham Suwarno, Iswanto Teguh Hidayat Iskandar Alam Tella, Fitriyani Wijaya, Setiawan Ardi