Articles
Improvement Naive Bayes Menggunakan Forward Selection, Information Gain dan Gain Ratio untuk Penanganan Independensi Fitur
Suprapto, Suprapto
Jurnal Sosial Teknologi Vol. 5 No. 4 (2025): Jurnal Sosial dan Teknologi
Publisher : CV. Green Publisher Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.59188/jurnalsostech.v5i4.32084
Penelitian ini bertujuan untuk menganalisis peningkatan kinerja algoritma Naive Bayes (NB) dalam menangani independensi fitur menggunakan metode Forward Selection, Information Gain, dan Gain Ratio. Naive Bayes merupakan algoritma klasifikasi yang sering digunakan karena efisiensi komputasinya yang tinggi, namun sering mengalami penurunan performa ketika ada ketergantungan antar fitur. Penelitian ini menggunakan pendekatan eksperimental dengan menerapkan beberapa algoritma, yakni Naive Bayes, Forward Selection Naive Bayes (FSNB), Forward Selection Information Gain Naive Bayes (FSIGNB), dan Forward Selection Information Gain Ratio Naive Bayes (FSIGRNB) pada dataset berdimensi tinggi. Metode validasi yang digunakan adalah 10-fold cross validation untuk mengukur akurasi setiap algoritma. Hasil penelitian menunjukkan bahwa algoritma FSNB dan FSIGNB berhasil meningkatkan akurasi secara signifikan dibandingkan dengan algoritma NB standar. FSNB memiliki akurasi rata-rata tertinggi sebesar 81,124%, diikuti oleh FSIGNB dan FSIGRNB. Implikasi dari penelitian ini adalah bahwa penerapan metode Forward Selection, Information Gain, dan Gain Ratio dapat meningkatkan akurasi klasifikasi Naive Bayes, terutama dalam dataset dengan dimensi fitur yang tinggi, serta memberikan kontribusi penting dalam pengembangan algoritma untuk menangani independensi fitur.
Redesigning the Boundaries of Corruption in Government Procurement of Goods and Services
Andi Akbar Subari;
Achmad Faisal;
Suprapto Suprapto
International Journal of Sociology and Law Vol. 2 No. 3 (2025): August : International Journal of Sociology and Law
Publisher : Asosiasi Penelitian dan Pengajar Ilmu Hukum Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.62951/ijsl.v2i3.790
Government procurement, particularly in Indonesia, remains highly susceptible to corruption due to systemic regulatory loopholes and excessive human discretion, often characterized by collusion and bid-rigging. This institutional vulnerability defines the traditional "boundaries of corruption" as the discretionary corridors within existing administrative law. This research aims to fundamentally redesign these boundaries by shifting control from human discretion to technological enforcement. This study employs normative legal research focusing on the Presidential Regulation on Procurement, integrated with a technological design approach relevant to the journal. The core contribution is a reform model proposing the mandatory integration of AI-powered Smart Contracts and Distributed Ledger Technology (Blockchain) into the public procurement process. Key findings indicate that the primary corrupt boundary lies in ambiguous clauses concerning direct appointments and contract amendments. We propose that an AI-based system can monitor real-time pricing anomalies and bidder networks (network analysis), while Smart Contracts can automate and audit execution, thereby eliminating human factor vulnerability. This redesign transforms the boundaries of corruption from a matter of criminal enforcement to one of algorithmic inevitability, providing a robust, transparent, and self-auditing framework for digital governance.
Meningkatkan Belajar Siswa dengan Metode Prablem Based Learning pada Kelas 8 SMPN 4 Tanjung Lago Kab. Banyuasin Sumatera Selatan
Suprapto, Suprapto;
Umar, Firman;
Karim, Abdul
JURNAL PEMIKIRAN DAN PENGEMBANGAN PEMBELAJARAN Vol. 4 No. 1 (2022): JURNAL PEMIKIRAN DAN PENGEMBANGAN PEMBELAJARAN (JP-3)
Publisher : RAYHAN INTERMEDIA
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
Penelitian tindakan ini bertujuan untuk mengetahui pengaruh model pembelajaran Prablem Based Learning (PBL) dalam meningkatkan minat belajar siswa terhadap mata pelajaran IPS. Salah satu faktor penting pemakaian model pembelajaran ini karena pada kompetensi dasar tentang masalah perpajakan perlu mendapat penekanan tertentu. Hal ini diperlukan karena apresiasi siswa SMPN 4 Tanjung Lago mengenai masalah perpajakan masih rendah. Diharapkan dengan tingkat apresiasi yang baik terhadap permasalahan perpajakan dapat menjadi bekal hidup bermasyarakat. Penelitian tindakan ini dilaksanakan pada bulan Mei sampai dengan Juli 2019 pada kelas VIII SMP N 4 Tanjung Lago, dan dilaksanakan dalam dua siklus. Pelaksanannya melalui tahapan : menentukan kompetensi dasar masalah perpajakan, menyusun RPP tentang perpajakan, menentukan instrumen yang akan dipakai sebagai tolok ukur pencapaian, menentukan dan melaksanakan model pembelajaran Prablem Based Learning (PBL) yang dibagi menjadi tiga tahap : pelaksanaan bermain peran dan diskusi kelompok, analisa keberhasilan dan kekurangannya dan kesimpulan Dari hasil penelitian dapat disimpulkan bahwa pelaksanaan model pembelajaran Prablem Based Learning (PBL) dapat meningkatkan minat belajar siswa kompetensi dasar perpajakan. Hal ini dapat dilihat dari hasil catatan observasi, peningkatan nilai pretes maupun pos tes baik pada siklus kesatu maupun kedua maupun dari hasil angket siswa.
Adsorption of Remazol Blue And Indigosol Yellow Mixed Dyes Using Bidara Arab Leaves (Ziziphus spina-christi)
Kurnia, Mega;
Suprapto, Suprapto;
Ni'mah, Yatim Lailun
Indonesian Journal of Chemical Analysis (IJCA) Vol. 7 No. 1 (2024): Indonesian Journal of Chemical Analysis
Publisher : Universitas Islam Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.20885/ijca.vol7.iss1.art3
In this study, the adsorption of Remazol Blue and Indigosol Yellow using Bidara Arab leaves (Ziziphus spina-christi) as adsorbents was investigated through batch adsorption. The experimental parameters included contact time, adsorbent mass, initial concentrations, and pH. UV-Vis spectrophotometer was employed to measure the adsorption results at the maximum wavelength of each dye. The research was conducted in triplicate, and a t-test, "Paired Two Sample for Means", with a standard deviation <2% was employed for statistical analysis. Optimal adsorption conditions were achieved at a contact time of 45 minutes, an adsorbent mass of 45 mg, an initial concentration of 30 ppm, and a pH of 3. The results indicated that Bidara Arab leaves effectively reduced the concentration of the mixed dyes with %decoloration up to 99,79% on Remazol Blue and 99,50% on Indigosol Yellow.
The Identification of Acetic Acid-Ethanol Mixture Using Gas Sensor Array and Ensemble Regression
Suprapto, Suprapto;
Yatim Lailun Ni'mah;
Harmami, Harmami;
Ulfin, Ita;
Ardiyanti, Annisa
Indonesian Journal of Chemical Analysis (IJCA) Vol. 7 No. 1 (2024): Indonesian Journal of Chemical Analysis
Publisher : Universitas Islam Indonesia
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.20885/ijca.vol7.iss1.art1
Identification of acetic acid-ethanol mixtures using a commercial gas sensor array equipped with ensemble regression has been carried out. The gas sensor analysis was simple, rapid, and fast since it did not require any sample preparation. A quantitative analysis of the acetic acid-ethanol mixture was carried out to determine the sensitivity and selectivity of the sensor in distinguishing the concentration of the acetic acid and ethanol mixture. This study focuses on the coefficient of determination of 80% of the calibration data set and recovery of 20% of the testing data set. The models showed excellent performance,specifically, the Bagging and Random Forest r2 for the ethanol calibration data reached 0.91 and 0.94, respectively. The corresponding ethanol test recoveries were 99.95% and 97.84%, indicating the robustness of the model in accurately predicting ethanol concentration. Acetic acid test recoveries were 100.56% and 101.38% with r2 of 0.89 and 0.93 for Bagging and Random Forest regression, respectively. Hence, the commercial gas sensor array equipped with ensemble regression can be applied to the quantification of the acetic acid – ethanol mixture and demonstrate opportunities for the practical use of this gas sensor array in analyzing real samples, i.e. human breath or environmental monitoring samples.
Twitter Sentiment Towards 2024 Jakarta Governor Candidates With Naïve Bayes Algorithm
Abei, Fikri;
Sulaeman, Asep Arwan;
Suprapto, Suprapto
Journal of Computer Networks, Architecture and High Performance Computing Vol. 7 No. 1 (2025): Article Research January 2025
Publisher : Information Technology and Science (ITScience)
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47709/cnahpc.v7i1.5358
This study aims to analyze public sentiment towards candidates for the 2024 Governor of DKI Jakarta through the Twitter platform, with a focus on classifying positive and negative sentiment. Along with the rapid development of social media, Twitter has become the main channel for people to voice political opinions. Sentiment analysis was conducted using the Naive Bayes algorithm to classify the sentiment of tweets collected through crawling techniques during the campaign period. The data used includes user tweets, with features such as frequently occurring words, popular hashtags, and discussion topics related to each gubernatorial candidate. The results showed that the Naive Bayes algorithm provided the best performance in classifying sentiment data in the period August 1 to December 26, 2024, with the highest accuracy rate reaching 75% at a data ratio of 90:10. This research also identified challenges in sentiment classification, such as the presence of new terms in test documents that are not recognized by the training model. The findings are expected to provide a clearer picture of public perceptions of gubernatorial candidates and contribute to the analysis of political sentiment on social media
Implementasi Project Based Learning (PjBL) Berorientasi Pengembangan Karakter Siswa yang Kritis
Suprapto, Suprapto;
Sulaeman, Maryam
Jurnal Inovasi Pendidikan MH Thamrin Vol. 6 No. 2 (2022): Jurnal Inovasi Pendidikan MH Thamrin
Publisher : LPPM Universitas Mohammad Husni Thamrin
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37012/jipmht.v6i2.1208
The Distance Learning Process is a solution to the Covid-19 pandemic situation which is considered more effective and efficient, but there are various kinds of problems, not only educators and students, but also parents. The problems faced are the difficulty of supervising students who lack honesty and discipline in doing and collecting assignments, supervising students who do not focus on learning, difficult to adapt which make character development less effective. The specific purpose of the research is to produce a Project Based Learning model that can improve students' ability to solve problems, and it is hoped that students will be more active, independent and responsible. The method used is Action Research to produce certain products, and test the effectiveness of the product through various stages and validation with the following steps: 1) planning, 2) acting, 3) monitoring, and 4) reflecting. The results of the study found that scores were still very lacking in the first and second cycles in fostering a critical attitude to students, but in the third cycle significant improvements were found. This is evidenced in the reflection of most students. Future research requires a model for applying critical thinking in higher education
Pengaruh Media Pembelajaran Terhadap Hasil Belajar Siswa
Inayatullah, Putri Asti;
Suprapto, Suprapto;
Nadiah, Nadiah
Juwara: Jurnal Wawasan dan Aksara Vol. 4 No. 2 (2024)
Publisher : Yayasan Pendidikan dan Pengembangan Harapan Ananda
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.58740/juwara.v4i2.229
This study aims to examine the effect of the Kahoot learning media on student learning outcomes at SMK Pelita Tiga Jakarta. The use of Kahoot as a learning media was chosen due to its efficiency, innovativeness, and ability to help achieve learning objectives at a lower cost. The research method used is a quantitative approach with a correlation method. This study involved 24 students selected using the Cluster Sampling technique. Data collection was conducted through questionnaires and documentation, while data analysis was performed using the product moment correlation technique. Based on calculations, the product moment correlation value for 24 degrees of freedom (df) at a 5% significance level is 0.404, and at a 1% significance level is 0.515. The analysis results show that the observed correlation value (ro) of 0.617 is greater than the table value (rt) at both significance levels. Therefore, the null hypothesis is rejected, and the alternative hypothesis is accepted, indicating a positive effect of Kahoot learning media on student learning outcomes at SMK Pelita Tiga Jakarta. The implication of this study is that Kahoot can be an effective alternative learning media to improve student learning outcomes.
Digitalisasi Tandatangan Elektronik pada Akta Notaris
Omiyani*, Selva;
Suprapto, Suprapto;
Saprudin, Saprudin
JIM: Jurnal Ilmiah Mahasiswa Pendidikan Sejarah Vol 8, No 4 (2023): Agustus, Social Religious, History of low, Social Econmic and Humanities
Publisher : Universitas Syiah Kuala
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.24815/jimps.v8i4.26654
Penelitian ini menganalisis kepastian hukum tanda tangan yang berbasis elektronik ketika diterapkan pada akta yang berkekuatan hukum dan pembuktian yang autentik, dibuat oleh notaris dan untuk memberikan peraturan perundang-undangan yang akan datang untuk konsep cybernotary yang diterapkan oleh notaris di Indonesia. Penelitian Hukum Normatif menjadi metode penelitian yang digunakan dalam artikel penelitian ini. Hasil penelitian menjelaskan Pertama, tandatangan elektronik di Indonesia belum dapat diterapkan karena terkendala dengan kewajiban dari Jabatan Notaris yang ada pada Pasal 16 UUJN. Namun pada penjelasannya tersebut memberi peluang diterapkannya cyber notary di Indonesia. Adapun kelebihan tandatangan elektronik jika diterapkan yaitu waktu yang lebih efesien, kekuatan hukumnya sama dengan tandatangan konvensional atau tandatangan basah, identitas terjamin, hemat biaya pengeluaran dan eco friendly. Kedua, cybernotary untuk saat ini dapat diterapkan terbatas hanya pada waarmerking dan legalisasi karena keduanya merupakan surat bawah tangan yang disahkan notaris sehingga tidak akan terdegradasi. Selain itu, Salinan akta dapat diterapkan karena Salinan akta hanya memerlukan tandatangan notaris sehingga dapat ditandatangani menggunakan tandatangan elektronik. Untuk formulasi kedepan mengenai hukum positif yang berlaku yaitu merevisi Pasal 16 UUJN dan merevisi Pasal 5 UU ITE.
The Impact of Islamic Education on Local Communities in Indonesia: Systematic Literature Review
Karim, Syaban Abdul;
Suprapto, Suprapto;
Quddus, Abdul
QALAMUNA: Jurnal Pendidikan, Sosial, dan Agama Vol. 16 No. 2 (2024): Qalamuna - Jurnal Pendidikan, Sosial, dan Agama
Publisher : Lembaga Penerbitan dan Publikasi Ilmiah Program Pascasarjana IAI Sunan Giri Ponorogo
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.37680/qalamuna.v16i2.6025
Islamic education has a vital role in shaping the character and culture of local communities in Indonesia. This study specifically aims to examine the influence of Islamic education on the social, cultural, and educational dynamics within local communities in Indonesia through the Systematic Literature Review (SLR) approach, focusing on the stages of identification, selection, and synthesis of relevant studies. The study identifies and synthesizes findings from multiple related studies published over the past ten years. In this study, 94 articles were identified through Google Scholar, but after a selection process based on inclusion and exclusion criteria, 25 articles were selected for further analysis. Based on a thorough analysis of 25 selected articles, the study results demonstrate that Islamic education contributes significantly to social and cultural change, strengthening local values and fostering an adaptive curriculum. In addition, Islamic education also plays a vital role in countering radicalism and promoting social harmony. However, there are challenges in integrating traditional values with modern educational needs. The study provides in-depth insights for policymakers and educators to develop more effective and responsive education strategies to the needs of local communities in Indonesia.