Claim Missing Document
Check
Articles

Found 40 Documents
Search

An Explainable AI Model for Hate Speech Detection on Indonesian Twitter Muhammad Amien Ibrahim; Samsul Arifin; I Gusti Agung Anom Yudistira; Rinda Nariswari; Abdul Azis Abdillah; Nerru Pranuta Murnaka; Puguh Wahyu Prasetyo
CommIT (Communication and Information Technology) Journal Vol. 16 No. 2 (2022): CommIT Journal
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v16i2.8343

Abstract

To avoid citizen disputes, hate speech on social media, such as Twitter, must be automatically detected. The current research in Indonesian Twitter focuses on developing better hate speech detection models. However, there is limited study on the explainability aspects of hate speech detection. The research aims to explain issues that previous researchers have not detailed and attempt to answer the shortcomings of previous researchers. There are 13,169 tweets in the dataset with labels like “hate speech” and “abusive language”. The dataset also provides binary labels on whether hate speech is directed to individual, group, religion, race, physical disability, and gender. In the research, classification is performed by using traditional machine learning models, and the predictions are evaluated using an Explainable AI model, such as Local Interpretable Model-Agnostic Explanations (LIME), to allow users to comprehend why a tweet is regarded as a hateful message. Moreover, models that perform well in classification perceive incorrect words as contributing to hate speech. As a result, such models are unsuitable for deployment in the real world. In the investigation, the combination of XGBoost and logical LIME explanations produces the most logical results. The use of the Explainable AI model highlights the importance of choosing the ideal model while maintaining users’ trust in the deployed model.
IMPLEMENTASI KRIPTOGRAFI KURVA ELIPTIK ELGAMAL DI LAPANGAN GALOIS PRIMA PADA PROSES ENKRIPSI DAN DEKRIPSI BERBANTUAN SOFTWARE PYTHON Ummu Wachidatul Latifah; Puguh Wahyu Prasetyo
Journal of Fundamental Mathematics and Applications (JFMA) Vol 4, No 1 (2021)
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2057.193 KB) | DOI: 10.14710/halal.v%vi%i.9278

Abstract

Perkembangan teknologi memberikan dampak terhadap kemajuan di segala bidang kehidupan manusia terutama dalam bidang informasi. Hal ini memberikan dampak positif dan negatif. Salah satu dampak positifnya adalah mudahnya bertukar informasi dari yang bersifat umum atau rahasia melalui internet. Dampak negatifnya adalah data yang bersifat rahasia menjadi kurang aman dan dapat disalahgunakan oleh pihak yang tidak berwenang. Kriptografi kurva eliptik El-Gamal (ECC: Eliptic Curve Cryptosystem) memberikan solusi untuk keamanan suatu informasi. ECC merupakan salah satu metode kriptografi kunci publik yang mempunyai tingkat keamanan tinggi dibandingkan dengan algoritma kunci publik lainnya. Tujuan dari penelitian ini adalah memahami konsep kriptografi kurva eliptik El-Gamal yang akan didefinisikan di Galois field prima. Hasil dari penelitian ini, yaitu penggunaan kurva eliptik El-Gamal di Galois field prima untuk proses pembentukan kunci, proses enkripsi dan proses dekripsi pada suatu data dengan menggunakan Python.
BEBERAPA SIFAT (R,S)-SUBMODUL PRIMA-α GABUNGAN Dian Ariesta Yuwaningsih; Rusmining Rusmining; Puguh Wahyu Prasetyo
Journal of Fundamental Mathematics and Applications (JFMA) Vol 4, No 2 (2021)
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1132.22 KB) | DOI: 10.14710/jfma.v4i2.12105

Abstract

Diberikan  dan  merupakan ring komutatif. Keprimaan pada suatu ring telah mengalami perkembangan ke dalam struktur modul. Namun, definisi keprimaan yang ada selama ini hanya berfokus pada operasi pergandaan skalar di dalam modul. Submodul prima-α  merupakan salah satu perumuman dari submodul prima yang melibatkan operasi aditif dan pergandaan skalar di dalam modul. Pada artikel ini disajikan generalisasi dari submodul prima-α  ke dalam struktur (R,S)-modul, yang selanjutnya disebut (R,S)-submodul prima-α  gabungan. Selanjutnya, disajikan beberapa sifat dari (R,S)-submodul prima-α  gabungan. Beberapa sifat tersebut diantaranya adalah syarat perlu dan syarat cukup suatu (R,S)-submodul membentuk (R,S)-submodul prima-α  gabungan; sifat (R,S)-submodul prima-α  gabungan yang berkaitan dengan homomorfisma (R,S)-modul; serta syarat perlu dan syarat cukup suatu (R,S)-submodul faktor membentuk (R,S)-submodul prima-α  gabungan. Beberapa sifat (R,S)-submodul prima-α  gabungan tersebut diperoleh dari pengembangan sifat keprimaan dalam struktur modul.
RADIKAL SUPERNILPOTENT BERTINGKAT Puguh Wahyu Prasetyo
Journal of Fundamental Mathematics and Applications (JFMA) Vol 2, No 1 (2019)
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (175.192 KB) | DOI: 10.14710/jfma.v2i1.25

Abstract

The development of Ring Theory motivates the existence of the development of the Radical Theory of Rings. This condition is motivated since there are rings which have properties other than those owned by the set ring of all integers. These rings are collected so that they fulfill certain properties and they are called radical classes of rings. As the development of science about how to separate the properties of radical classes of rings motivates the existence of supernilpotent radical classes. On the other hand, there exists the concept of graded rings. This concept can be generalized into the Radical Theory of Rings. Thus, the properties of the graded supernilpotent radical classes are very interesting to investigate. In this paper, some graded supernilpotent radical of rings are given and their construction will be described. It follows from this construction that the graded Jacobson radical is a graded supernilpotent radical.
Penerapan Model Discovery Learning Untuk Meningkatkan Keaktifan Belajar Siswa Saat Pandemi Yoga Handita Handita; Puguh Wahyu Prasetyo; Sugiyem Sugiyem
Jurnal Derivat: Jurnal Matematika dan Pendidikan Matematika Vol. 9 No. 1 (2022): Jurnal Derivat (Juli 2022)
Publisher : Pendidikan Matematika Universitas PGRI Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (936.841 KB) | DOI: 10.31316/j.derivat.v9i1.2990

Abstract

The education sector is feeling the impact of the COVID-19 pandemic. During the pandemic, the procedure for teaching and learning activities (TLA) changes according to the circumstances, this greatly affects the level of student learning activity (SLA). The purpose of this study is to improve SLA using the discovery learning mode (DLM) which is accompanied by the TPACK approach in mathematics teaching and learning. The type of research used is classroom action research (CAR), in this CAR it uses two cycles and each cycle has two meetings. This PTK takes the research subject, namely students of class X MIPA 2 SMAN 1 Bantul in the even semester of the 2021/2022 academic year. The results of this CAR show that there is an increase in SLA in mathematics learning using MDL. The increase in the SLA value can be seen from the pre-cycle results with the percentage value of 62.8% increasing to 71.42% after going through the action during the first cycle, then during the second cycle there was an increase with the percentage value of 89.7%. In cycle II, all SLA indicators have reached the desired criteria. The desired SLA criteria are with a minimum score percentage of 75% with high criteria.Keywords: discovery learning, Classroom Action Research, Student Learning Activity
Pelabelan Jarak Tak Teratur Titik Pada Graf Persahabatan Lengkap Diperumum Cindy Ainun Majid; Dian Eka Wijayanti; Aris Thobirin; Puguh Wahyu Prasetyo
Limits: Journal of Mathematics and Its Applications Vol 20, No 1 (2023)
Publisher : Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/limits.v20i1.7917

Abstract

Graph labeling is the labeling of graph elements such as vertex, edge and both. distance vertex irregular labeling is a type of labeling resulting from the development of distance magic labeling and (a, b)-distance anti-magic labeling.  Let   , be a simple graph.  The distance vertex irregular labeling of  is a vertex labeling so that the weight of each vertex    is different. The weight of    is calculated based on the sum of vertices  label  in  the set of neighboring vertex , namely  Distance vertex  irregularity  strength of   , denoted as d , is the smallest value of the largest label  so that  has a distance vertex irregular labeling.  This study aims to construct a generalized complete friendship graph , determine the labeling function, determine the distance vertex irregularity strength then formulate and prove the theorem resulting from the labeling. The object of this research is to label each vertex on a generalized complete friendship graph. This research method is a literature study obtained through various sources. Based on the research results, it is known that the graph  has distance vertex irregular labeling. For an integer m and n, , the  labeling  function of   is  and . Distance vertex  irregularity  strength of generalized complete friendship graph is   .
Pengembangan e-LKM Terintegrasi Literasi Numerasi untuk Meningkatkan Berpikir Kritis pada Materi Analisis Vektor Nur Robiah Nofikusumawati Peni; Sumargiyani Sumargiyani; Puguh Wahyu Prasetyo
Jurnal Tadris Matematika Vol 6 No 1 (2023)
Publisher : Universitas Islam Negeri Sayyid Ali Rahmatullah Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21274/jtm.2023.6.1.115-128

Abstract

Students' low reading interest greatly affects learning outcomes in Vector Analysis class. This is due to the rare interaction between students and learning resources in class. To increase student activity in reading and understanding the concept of vector analysis material, an e-LKM product is needed. This study aims to develop Student Worksheets (LKM) in electronic form that is integrated with numeracy literacy which can be used for learning vector analysis courses by knowing the validity and practicality of procedures so that the use of these e-LKM can improve students' critical thinking. This development research uses the ADDIE model (Analysis, Design, Development, Implementation, and Evaluation). Furthermore, the evaluation stage is carried out at each stage to improve the e-LKM that is made. The subjects were 21 students in semester VI of class C Mathematics Education FKIP Universitas Ahmad Dahlan. The research data was obtained by collecting questionnaires from material experts, media, and students' responses to the practicality of the media being developed. From the results of the questionnaires distributed, the average questionnaire from the two material experts and media experts showed excellent criteria with a mean score of 4.611 and 4.47 respectively. The results of student responses to product use show excellent criteria with a mean score of 4.27. Based on these results, the e-LKM that is used is proven to be valid and practical.
Program Evaluation and Review Technique (PERT) Analysis to Predict Completion Time and Project Risk Using Discrete Event System Simulation Method Yudistira, I Gusti Agung Anom; Nariswari, Rinda; Arifin, Samsul; Abdillah, Abdul Azis; Prasetyo, Puguh Wahyu; Susyanto, Nanang
CommIT (Communication and Information Technology) Journal Vol. 18 No. 1 (2024): CommIT Journal
Publisher : Bina Nusantara University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21512/commit.v18i1.8495

Abstract

The prediction of project completion time, which is important in project management, is only based on an estimate of three numbers, namely the fastest, slowest, and presumably time. The common practice of applying normal distribution through Monte Carlo simulation in Program Evaluation and Review Technique (PERT) research often fails to accurately represent project activity durations, leading to potentially biased project completion prediction. Based on these problems, a different method is proposed, namely, Discrete Event Simulation (DES). The research aims to evaluate the effectiveness of the simmer package in R in conducting PERT analysis. Specifically, there are three objectives in the research: 1) develop a simulation model to predict how long a project will take and find the critical path, 2) create an R script to simulate discrete events on a PERT network, and 3) explore the simulation output using the simmer package in the form of summary statistics and estimation of project risk. Then, a library research with a descriptive and exploratory method is used for data collection. The hypothetical network is used to obtain the numerical results, which provide the predicted value of the project completion, the critical path, and the risk level. Simulation, including 100 replications, results in a predicted project completion time and a standard deviation of 20.7 and 2.2 weeks, respectively. The DES method has been proven highly effective in predicting the completion time of a project described by the PERT network. In addition, it offers increased flexibility.
Trend Analysis of the ARIMA Method: A Survey of Scholarly Works Arifin, Samsul; Manurung , Monica Mayeni; Jonathan, Stanley; Effendi, Melody; Prasetyo , Puguh Wahyu
Recent in Engineering Science and Technology Vol. 2 No. 03 (2024): RiESTech Volume 02 No. 03 Years 2024
Publisher : MBI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59511/riestech.v2i03.65

Abstract

Recent research trends in bibliometric analysis using the ARIMA method have attracted the attention of many researchers in this field. This study aims to conduct a thorough review of related studies that apply the ARIMA method in bibliometric analysis. The dataset used was taken from the Scopus Web using VOSviewer. The main objective of this study is to identify the latest research trends related to the use of the ARIMA method in bibliometric analysis. The results of the analysis show that the use of the ARIMA method in bibliometric analysis has increased significantly in the last few years. Studies using this method have made valuable contributions to understanding research trends and scientific developments in various fields. These findings provide important insights for practitioners and researchers in the field of bibliometric analysis and can be used as a practical guide for those who wish to use the ARIMA method in bibliometric analysis. In addition, this study also discusses the strengths and weaknesses of using the ARIMA method in bibliometric analysis. This method has advantages in its ability to identify and model trends well but also has some limitations regarding parameter selection and interpretation of results. Therefore, this study provides a more comprehensive understanding of the application of the ARIMA method in bibliometric analysis and encourages further research in addressing the challenges associated with using this method. The benefit of this research lies in its ability to provide valuable insights for researchers, practitioners, and policymakers in understanding the latest research trends in bibliometric analysis using the ARIMA method. The findings of this research can be used to make strategic decisions regarding the development and publication of scientific publications, as well as strengthen an understanding of research trends in certain fields. In conclusion, this study provides a comprehensive review of the latest research trends in bibliometric analysis using the ARIMA method. The findings and conclusions of this study provide a deeper understanding of the application of the ARIMA method in bibliometric analysis, as well as provide recommendations for further research in developing analytical methods and looking at new aspects of bibliometric analysis using the ARIMA method.
Development of Realistic Mathematics Education (RME)-Based Student Worksheet to Improve Students' Mathematical Communication Skills Samsinar, Samsinar; Mahmudah, Kunti Robiatul; Prasetyo, Puguh Wahyu
International Journal on Emerging Mathematics Education IJEME, Vol. 7 No. 2, September 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/ijeme.v7i2.28729

Abstract

AbstrakSalah satu tujuan utama pembelajaran matematika adalah untuk meningkatkan kemampuan komunikasi matematis karena kemampuan ini sangat penting untuk menyelesaikan berbagai masalah matematika. Faktanya kemampuan komunikasi matematis peserta didik di SMP Muhammadiyah 9 Yogyakarta masih termasuk dalam kriteria rendah berdasarkan hasil tes tertulis. Penelitian ini bertujuan untuk mengembangkan LKPD berbasis Realistic Mathematics Education untuk meningkatkan kemampuan komunikasi matematis peserta didik. Penelitian ini merupakan penelitian R&D dengan menggunakan model ADDIE. Instrumen yang digunakan adalah instrumen validasi, angket respon peserta didik, dan soal pretest dan posttest. Berdasarkan uji validitas, LKPD berbasis RME termasuk dalam kategori baik dari segi materi dengan skor rata-rata 113 dan sangat baik dari segi media dengan skor rata-rata 83. Berdasarkan angket peserta didik, LKPD berbasis RME termasuk dalam kategori baik dengan skor rata-rata 54,38 yaitu praktis. Berdasarkan hasil analisis nilai posttest kelas eksperimen dan kelas kontrol, LKPD berbasis RME efektif digunakan untuk meningkatkan kemampuan komunikasi matematis peserta didik. AbstractOne of the main goals of learning mathematics is to improve mathematical communication skills because these skills are very important for solving various mathematical problems. The mathematical communication skills of students at SMP Muhammadiyah 9 Yogyakarta are still included in the low criteria based on written test results. This research aims to develop Realistic Mathematics Education-based LKPD to improve students' mathematical communication skills. This research is an R&D research using the ADDIE model. The instruments used are validation instruments, student response questionnaires, and pretest and posttest questions. Based on the validity test, the RME-based LKPD is included in the good material category with an average score of 113 and very good in terms of media with an average score of 83. Based on the students' questionnaire, RME-based LKPD is included in the good category with an average score of 54.38, which is practical. Based on the results of the analysis of posttest scores of experimental and control classes, RME-based LKPD is effectively used to improve students' mathematical communication skills.