Article Per Year (5 Year)
p-Index From 2021 - 2026
0.983
P-Index
This Author published in this journals
All Journal Jurnal Ilmu Komputer dan Agri-Informatika JURTEKSI Ekasakti Jurnal Penelitian dan Pengabdian (EJPP) Jurnal Puan Indonesia TOFEDU: The Future of Education Journal
Gustri Efendi
Universitas Nahdlatul Ulama Sumatera Barat
Agriculture, Biological Sciences & Forestry Computer Science & IT Economics, Econometrics & Finance Education Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Mathematics Public Health Other

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
K-Nearest Neighbor untuk Frasa Guna Mendukung Keputusan dalam Mencari Guru Terbaik Januardi Nasir; Roni Saputra; Gustri Efendi; April Zahmi; Yasha Langitta Setiawan
Jurnal Ilmu Komputer dan Agri-Informatika Vol 9 No 1 (2022)
Publisher : Departemen Ilmu Komputer, Institut Pertanian Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/jika.9.1.13-22

Abstract

There are several ways to assess the best teacher in determining the potential teacher. This aims to encourage teachers to excel and see the motivation, dedication, and loyalty of teachers, as well as see the professionalism of a teacher in technological advancements based on 4.0. From the research conducted in determining the best teacher, there are problems, including in the selection of the best teacher, the principal tends to choose based on observations made only by the principal himself and does not pay attention to the criteria and indicators of assessment in the form of professional, personality and social which makes the teachers less than optimal in their work. Therefore we need a system to solve some of the problems that occur. A system was built to overcome the problem in the form of a decision support system. A decision support system is a system aimed at management in helping to make the right decisions. The method used is K-Nearest Neighbor, which is a method for making decisions using supervised learning where the results of the new input data are classified based on the closest in the value data. Calculations were carried out in 2020 and 2021. The total value of data in the previous year was 70 lines of data. If it is further detailed, the data used is 1190 value data. The assessment prediction data used is teacher data in 2021, as many as 37 lines of data. The k-NN algorithm uses the value of k to determine the number of nearest neighbors whose status will be calculated.
COMPARISON SVM, RF, BERT PUBLIC SENTIMENT DATA MBG IN X Gustri Efendi; Yandi, Rus; Aprilia, Rani; Amaroh Bit Taqwa, Irvan
JURTEKSI (jurnal Teknologi dan Sistem Informasi) Vol. 12 No. 1 (2025): Desember 2025
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Royal Kisaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v12i1.4170

Abstract

Abstract: MBG is a strategic program of the Prabowo-Gibran administration. This program has become a widely discussed issue in the public. To better understand public perception of this program, sentiment analysis is necessary. This study aims to compare the performance of algorithms machine learning SVM, RF, And BERT with preprocessing data analyzing public sentiment of the MBG program in media X. The total dataset for this study was 39,858 out of 42,465 successfully crawled tweets. The research methods included data collection, preprocessing data (cleaning, case folding, word normalization, stopword removal and stemming), feature extraction, model training (fine-tuning), handling class imbalance with SMOTE, and evaluation using accuracy, precision, recall, and f1-score. The research results show that without SMOTE, the best performing models are BERT with 89% accuracy, SVM 87%, and RF 78.4%. After SMOTE, the best algorithms were SVM with 92.94%, BERT with 88.3%, and RF with 86.59%. The results confirmed that SVM is the best algorithm if at leastclass imbalance. BERT is the best algorithm before and after SMOTE, because BERT is more effective in capturing the nuances of language on social media, so BERT is the most recommended in MBG sentiment analysis. Keywords: sentiment analysis; machine learning; SVM, RF, and BERT Abstrak: MBG merupakan program strategis pemerintahan Prabowo - Gibran. Program ini menjadi isu yang banyak diperbincangkan publik. Untuk mengetahui lebih dalam persepsi masyrakat tentang program ini, perlu dilakukan analisis sentiment. Penelitian ini bertujuan membandingkan kinerja algoritma machine learning SVM, RF, dan BERT dengan preprocessing data menganalisis sentiment public program MBG di media X. Total dataset penelitian ini adalah 39.858 dari 42.465 tweet yang berhasil di crawling. Metode penelitian mencakup pengumpulan data, preprocessing data (cleaning, case folding, normalisasi kata, stopword removal dan stemming), ekstraksi fitur, pelatihan model (fine-tuning), penanganan class imbalance dengan SMOTE, dan evaluasi menggunakan akurasi, presisi, recall, dan f1-score. Hasil peneltian menunjukkan, tanpa SMOTE model dengan kinerja terbaik adalah BERT dengan akurasi 89%, SVM 87%, dan RF 78,4%. Setelah SMOTE algoritma terbaik adalah SVM 92,94%, BERT 88,3% dan RF 86,59%. Hasil penelitian menegaskan bahwa SVM adalah algoritma terbaik jika minimal class imbalance. BERT adalah algoritma terbaik sebelum dan sesudah SMOTE, karena BERT lebih efektif dalam menangkap nuansa bahasa pada media sosial, sehingga BERT paling di rekomendasikan dalam analisis sentimen MBG. Kata kunci: analisis sentimen; machine learning; SVM, RF, dan BERT
Sosialisasi Pencegahan Kekerasan terhadap Anak dan Perempuan dalam Perspektif Hukum Perlindungan Anak dan Perempuan di Nagari Kasang, Kecamatan Batang Anai, Kabupaten Padang Pariaman Rangga Prayitno; Radiyan Rahim; Rica Azwar; April zahmi; Ade Triawan; Gustri Efendi
Ekasakti Jurnal Penelitian dan Pengabdian Vol. 5 No. 2 (2025): Ekasakti Jurnal Penelitian dan Pegabdian
Publisher : LPPM Universitas Ekasakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31933/ejpp.v5i2.1313

Abstract

Violence against children and women is a serious issue that threatens welfare, security, and human rights. In Padang Pariaman Regency, particularly in Nagari Kasang, cases still occur that reflect the community's low awareness of legal protection mechanisms. This outreach activity aims to increase public understanding of legal protection for children and women in accordance with Law No. 23 of 2004 on the Elimination of Domestic Violence and Law No. 35 of 2014 on Child Protection. The implementation methods included interactive legal lectures, group discussions, educational video screenings, and case reporting simulations to the authorities. Evaluation results from pre-tests and post-tests indicated a significant improvement in participants’ legal knowledge, from an average of 58% to 87%. The community also demonstrated increased awareness in reporting violence cases to the relevant authorities. Supporting factors included the commitment of local government officials and participants’ enthusiasm, while challenges faced were patriarchal culture and limited complaint facilities. This activity proves that community-based participatory outreach is effective in promoting violence prevention and strengthening legal protection for victims.
EDUKASI DAN PELATIHAN DATA SCIENCE UNTUK ANALISIS DATA KESEHATAN DALAM MENDUKUNG MASYARAKAT SEHAT DI KOTA PADANG PANJANG Januardi Nasir; Yasha Langitta Setiawan; Gustri Efendi; Lido Sabda Lesmana
PUAN INDONESIA Vol. 8 No. 1 (2026): Jurnal PUAN Indonesia Vol. 8 No. 1 Juli 2026
Publisher : ASOSIASI IDEBAHASA KEPRI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37296/jpi.v8i1.539

Abstract

The development of information technology has brought significant changes to various areas of life, including healthcare. One rapidly developing technology is data science, a discipline that utilizes data processing, statistics, and computational techniques to generate useful information to support decision-making. In healthcare, data science can be used to analyze health data, identify disease patterns, support disease prevention programs, and improve the quality of public health services. However, public understanding and skills in utilizing data science for health data analysis are still relatively limited. Therefore, a Community Service (PKM) activity themed "Data Science Education and Training for Health Data Analysis to Support a Healthy Community in Padang Panjang City" was implemented to improve public literacy and competency in utilizing data technology for healthcare.The activity implementation method included observation and identification of participant needs, program planning, delivery of educational materials, training in the use of RapidMiner software, practical health data analysis, and mentoring and evaluation of the activity. The materials provided covered basic data science concepts, data processing stages, data visualization, and the application of health data analysis using case studies relevant to community conditions. The results of the activity showed that participants gained increased knowledge and skills in understanding Data Science concepts and were able to perform simple health data analysis using RapidMiner. The high level of participant enthusiasm during the training demonstrated that this activity provided tangible benefits and was relevant to community needs. Overall, this activity successfully increased community capacity in utilizing health data as a basis for decision-making and supported the creation of a healthier, smarter, and data-driven society in Padang Panjang City.
The C4.5 Algorithm in Data Mining for Classifying Prospective Student Admissions (A Case Study of AMIK-DP) Rezki Fauzi; Gustri Efendi; Fitriany Fitriany
The Future of Education Journal Vol 5 No 2 (2026)
Publisher : Lembaga Penerbitan dan Publikasi Ilmiah Yayasan Pendidikan Tumpuan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61445/tofedu.v5i2.2138

Abstract

Algorithm c4.5 data classification algorithm bertipe decision tree. algorithm decision tree c4.5 built with a few stage that cover attribute election as root, make branch to every value and divide case in branch. tahap-tahan this be repeatinged to every branch until all cases in has class same. From decision tree completion so be got several rule a case. in this case author clasify pass from a student university at one particular college (AMIK Depati Parbo Kerinci) not only based on accomplishment index criteria komulatif but also extracurrucular skill likes practice labor, campus organization, assistant labor and age also be somebody yardstick to acceptable at a private resort / government. with algorithm applications c4.5 this can help side baak in recommend student university genuinely skilled.
Co-Authors Ade Triawan Amaroh Bit Taqwa, Irvan April Zahmi Aprilia, Rani Azwar, Rica Fitriany Fitriany januardi nasir Lido Sabda Lesmana Prayitno, Rangga Radiyan Rahim Rezki Fauzi Roni Saputra Rus Yandi Yasha Langitta Setiawan Yasha Langitta Setiawan