Article Per Year (5 Year)
p-Index From 2021 - 2026
2.64
P-Index
This Author published in this journals
All Journal JURNAL TEKNOLOGI DAN OPEN SOURCE JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Jurnal ICT : Information Communication & Technology Jurnal Teknologi Informatika dan Komputer Idealis : Indonesia Journal Information System Jurnal Pengabdian Masyarakat - Teknologi Digital Indonesia Jurnal Masyarakat Madani Indonesia Jurnal Pengabdian Masyarakat Bangsa Journal of Information System and Computer Journal of Artificial Intelligence and Technology Information Horizon: Indonesian Journal of Multidisciplinary
Mohamad Khoirul Ansor
Universitas Bhinneka PGRI
Agriculture, Biological Sciences & Forestry Arts Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Mathematics Medicine & Pharmacology Nursing Physics Public Health Social Sciences Other

Published : 20 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 20 Documents
Search

 1   2 
Multi-Sentence Contextual Modeling using Transformer Architecture for Arithmetic Operation Identification in Mathematical Word Problems Cikal Dwidyanto; Agung Prasetya; Mohamad Khoirul Ansor
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3431

Abstract

Mathematical word problems in Indonesian are generally presented as multi-sentence paragraphs, making the identification of arithmetic operations not solely dependent on recognizing numerical values, but also requiring an understanding of events and semantic relationships across sentences. This study formulates the task of arithmetic operation identification as a classification problem of a single primary operation into four classes: addition, subtraction, multiplication, and division. To capture contextual relationships across sentences, an encoder-based Transformer architecture is employed, which is capable of modeling long-range dependencies through a self-attention mechanism. The dataset consists of 900 elementary school-level mathematical word problems constructed in accordance with the Indonesian curriculum. Experimental results show that the model achieves an accuracy of 0.98 and an F1-score of 0.98. Per-class evaluation indicates high and consistent performance, although prediction errors are still observed in cases with ambiguous narrative patterns, particularly where addition is misclassified as multiplication or subtraction, and multiplication is misclassified as division. These findings demonstrate that the Transformer architecture is effective in leveraging multi-sentence context to improve the accuracy of arithmetic operation identification in mathematical word problems.
Design and Construction of a Website-Based Village Service System with Chatbot Integration Using the Extreme Programming Method (Case Study: Wonorejo Village, Sumbergempol) Dea Preciosa Santyana Putri; Mohamad Khoirul Ansor; Joko Iskandar
Jurnal Teknologi Informatika dan Komputer Vol. 12 No. 1 (2026): Jurnal Teknologi Informatika dan Komputer
Publisher : Universitas Mohammad Husni Thamrin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37012/jtik.v12i1.3440

Abstract

Public services at the village level are the spearhead of government services closest to the community. However, most villages in Indonesia still rely on manual systems for administrative management, including the process of submitting certificates, recording citizen data, and delivering information. Administrative services in Wonorejo Village, Sumbergempol District, are still carried out manually, causing various obstacles, such as inefficiency, long queues, service delays, and limited access to information for residents. This study aims to design and build a website-based village service system integrated with a chatbot to improve the effectiveness and efficiency of administrative services. The system was developed using the Extreme Programming (XP) method through two development iterations, utilizing the PHP-based Laravel framework, MySQL as the database, and Dialogflow as the Natural Language Processing (NLP) platform for the chatbot. The system's main features include online letter submission, application status monitoring, village information management, and an interactive chatbot. Functional testing was conducted using the black box testing method, while user acceptance was measured through a User Acceptance Test (UAT) using an ISO 25010-based instrument involving 12 respondents. The UAT results showed a satisfaction percentage of 95%, included in the very good category. The developed system has proven capable of supporting the digital transformation of public services at the village level.
Implementasi K-Nearest Neighbor (K-NN) Untuk Prediksi Kebutuhan Stok Pakan Kucing Di Ngunut Petshop Mohamad Khoirul Ansor; Fahrur Rozi; Rafif Mallow Dwi Syamsoe
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 9, No 4 (2024)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v9i4.9192

Abstract

Persaingan bisnis yang semakin ketat menuntut setiap pengusaha untuk mampu mengambil keputusan secara cepat dan tepat berdasarkan in-formasi yang akurat. Salah satu permasalahan yang dihadapi Ngunut Petshop adalah penumpukan stok pakan kucing akibat ketidaktepatan dalam memprediksi kebutuhan konsumen. Untuk mengatasi hal terse-but, penelitian ini menerapkan metode K-Nearest Neighbor (K-NN) sebagai teknik data mining guna memprediksi kebutuhan stok pakan kucing. Data yang digunakan berasal dari catatan penjualan Ngunut Petshop pada periode bulan Maret 2024 hingga Mei 2024, dengan atribut yang meliputi jenis kucing, umur kucing, jenis makanan, dan jenis kelamin. Proses penelitian dilakukan melalui tahapan data selec-tion, preprocessing, transformation, data mining, hingga interpreta-tion/evaluasi dengan menggunakan aplikasi WEKA sebagai alat bantu analisis. Hasil pengujian menunjukkan bahwa nilai k=41 dengan pro-porsi data latih 50% dan data uji 50% memberikan akurasi tertinggi sebesar 58%. Temuan ini menunjukkan bahwa meskipun metode K-NN dapat digunakan untuk membantu prediksi kebutuhan stok pakan kuc-ing, tingkat akurasi yang diperoleh masih rendah. Oleh karena itu, diperlukan penambahan jumlah data, penggunaan atribut tambahan, maupun penerapan metode klasifikasi lain sebagai pembanding agar hasil prediksi dapat lebih optimal dan mendukung pengambilan kepu-tusan manajemen stok secara lebih efektif di Ngunut Petshop.
Analisis Sentimen Pengguna Terhadap Game Minecraft pada Ulasan Google Play Menggunakan Metode Naïve Bayes dan Support Vector Machine (SVM) Syafi', Faiza; Ansor, Mohamad Khoirul; Prasetya, Agung
HORIZON: Indonesian Journal of Multidisciplinary Vol. 4 No. 4 (2026): HORIZON: Indonesian Journal of Multidisciplinary
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/hijm.v4i4.6768

Abstract

User reviews on digital platforms are an important source of information for understanding perceptions of game products, but the large amount of data makes manual analysis less effective. This study aims to analyze user sentiment towards the Minecraft game based on Google Play Store reviews and compare the performance of the Naïve Bayes and Support Vector Machine (SVM) methods. The study used a quantitative approach with 1,600 scraped reviews, which after preprocessing became 1,477 data. The research stages included text cleaning, sentiment labeling, TF-IDF feature extraction, data division using a stratified split, classification model development, and evaluation using accuracy, precision, recall, F1-score, and the McNemar test. The results showed that 70.3% of reviews had positive sentiment, 23.3% were negative, and 6.4% were neutral. The SVM model produced better performance with an accuracy of 82.09% and an F1-score of 0.79, compared to Naïve Bayes with an accuracy of 75.62% and an F1-score of 0.6788. However, the McNemar test results showed no significant difference in performance between the two models (p-value = 0.3074). This finding suggests that the SVM is superior in predictive performance, but both methods have relatively equivalent classification capabilities statistically in analyzing Minecraft user review sentiment.
Implementasi Extreme Programming (Xp) dalam Pembuatan Sistem Informasi PTSL Berbasis Website Menggunakan Laravel Dengan Integrasi Peta Digital GIS (Studi Kasus: Desa Bukur) Dewi, Alivia Prasetya; Ansor, Mohamad Khoirul; Kartika, Yayak
HORIZON: Indonesian Journal of Multidisciplinary Vol. 4 No. 4 (2026): HORIZON: Indonesian Journal of Multidisciplinary
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/hijm.v4i4.6903

Abstract

Complete Systematic Land Registration (PTSL) is a government program to provide legal certainty and protection for community land rights. However, PTSL data management in Bukur Village is still carried out manually using physical documents and Microsoft Excel, potentially causing process delays, data duplication, and file loss. This study aims to develop a website-based PTSL information system to improve the efficiency and transparency of land data management. The study used the Extreme Programming (XP) software development method, which includes iterative planning, design, coding, and testing stages. Data were collected through observation, interviews, and documentation. The system was developed using the Laravel framework, a MySQL database, and Leaflet-based Geographic Information System (GIS) integration to visualize land locations. System testing was conducted using Black Box Testing on 15 test scenarios that included authentication, file management, document upload, status monitoring, data export, and map visualization. The test results showed that all 15 scenarios were successfully executed according to the expected output with a 100% success rate. The developed system is able to integrate applicant and file data management, support application status monitoring, and present land location information visually. Thus, this website-based PTSL information system can be a solution to increase efficiency, reduce the risk of data management errors, and facilitate access to land information for admins and the public.
Analisis Groundedness Model LLM dalam Pembentukan Soal Cerita Matematika dari Teks Bacaan Berbahasa Indonesia Feri Andriawan Saputra; Agung Prasetya; Mohamad Khoirul Ansor
Journal of Artificial Intelligence and Technology Information (JAITI) Vol. 4 No. 3 (2026): Volume 4 Number 3 September 2026
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jaiti.v4i3.317

Abstract

Soal cerita matematika (Math Word Problem/MWP) merupakan instrumen evaluasi penting yang mengintegrasikan kemampuan literasi dan numerasi. Perkembangan Large Language Model (LLM) membuka peluang otomatisasi pembuatan MWP dari teks bacaan. Namun, tantangan utama adalah fenomena hallucination yang menurunkan kualitas pedagogis soal. Penelitian ini bertujuan: (1) mengembangkan kerangka evaluasi groundedness berbasis enam aspek sebagai produk utama, dan (2) mengevaluasi tingkat groundedness MWP yang dihasilkan model gemma3:1b dari teks bacaan berbahasa Indonesia. Pendekatan Research and Development (R&D) dengan model ADDIE digunakan. Enam aspek groundedness dikembangkan: Entity Consistency (EC), Event Consistency (EV), Context Alignment (CA), Semantic Alignment (SA), Numerical Groundedness (QN), dan Question Relevance (QR), masing-masing dinilai menggunakan skala biner 0–1. Evaluasi dilakukan terhadap 460 soal cerita matematika valid dari empat teks bacaan BSE SD Kurikulum Merdeka menggunakan model gemma3:1b dengan lima konfigurasi parameter (E1–E5). Hasil menunjukkan gemma3:1b grounded pada teks sederhana–menengah (Teks 1: 73,25%; Teks 3: 75,91%) namun gagal pada teks kompleks (Teks 4: 47,22%). Konfigurasi E3 (temperature=0,3; top_p=0,9) memberikan keseimbangan terbaik. Kerangka evaluasi terbukti reliabel dengan Cohen's Kappa 0,68–0,81.
Optimalisasi Media Pembelajaran di SMP Tahfidz Modern Lubabul Fattah melalui Pelatihan Pembuatan Game Edukatif Berbasis Wordwall Yayak Kartika Sari; Mohamad Khoirul Ansor; Joko Iskandar
Jurnal Pengabdian Masyarakat - Teknologi Digital Indonesia. Vol 5, No 1 (2026): Maret 2026
Publisher : Lembaga Penelitian dan Pengabdian Masyarakat - Universitas Teknologi Digital Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26798/jpm.v5i1.2250

Abstract

Perkembangan teknologi informasi dan komunikasi di era digital telah membawa perubahan signifikan dalam berbagai aspek kehidupan, termasuk dalam dunia pendidikan. Dalam konteks pendidikan di tingkat Sekolah Menengah Pertama (SMP), khususnya di lembaga yang mengusung konsep integrasi antara pendidikan umum dan agama seperti SMP Tahfidz Modern Lubabul Fattah, penggunaan media pembelajaran yang menarik dan kontekstual menjadi sangat penting. Siswa di sekolah ini diharapkan tidak hanya unggul dalam hafalan Al-Qur’an, tetapi juga mampu memahami materi pelajaran umum secara mendalam. Sayangnya, tantangan yang dihadapi guru adalah keterbatasan media pembelajaran yang mampu menjembatani kebutuhan tersebut. Salah satu solusi yang dapat digunakan untuk menjawab tantangan ini adalah penerapan aplikasi Wordwall dalam pembelajaran. Evaluasi dari tim pengabdi untuk mengetahui tingkat pemahaman peserta dengan memberikan soal Pre-Test dan Post- Test. Peserta yang mengikuti dari awal sampai akhir mengalami peningkatan pengetahuan yang dapat dilihat dari hasil pembandingan nilai pre test dengan nilai post test dengan hasil rata-rata Pre-Test yaitu62. Setelah dilakukan Post-Test meningkat menjadi 92,67. Peserta kegiatan mencakup guru SMP Tahfidz Modern Lubabul Fattah. Peserta juga mengisi kuisoner untuk mengetahui Tingkat kepuasan terhadap pelatihan media interaktif dengan menggunakan Wordwall. Tingkat kepuasan diperoleh nilai rata-rata skala penilaian 5 yaitu 18 dan rata-rata skala penilaian 4 yaitu 12 sehingga dapat disimpulkan bahwa kegiatan memuaskan peserta kegiatan
Analisis Usability dan User Experience Sistem Informasi Primary Care BPJS Kesehatan di Puskesmas Karanganyar Menggunakan Metode System Usability Scale (SUS) dan User Experience Questionnaire (UEQ) Sya’bana, Malfiana Rizqina Luthfillah; Rozi, Fahrur; Ansor, Mohamad Khoirul
HORIZON: Indonesian Journal of Multidisciplinary Vol. 4 No. 3 (2026): HORIZON: Indonesian Journal of Multidisciplinary
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/gzqch503

Abstract

Penelitian ini bertujuan menganalisis tingkat usability dan user experience Sistem Informasi Primary Care (P-Care) BPJS Kesehatan di Puskesmas Karanganyar, Kecamatan Gandusari, Kabupaten Trenggalek. P-Care adalah aplikasi berbasis web yang wajib digunakan seluruh fasilitas kesehatan tingkat pertama (FKTP) dalam mengelola pelayanan peserta Jaminan Kesehatan Nasional (JKN). Penelitian menggunakan pendekatan kuantitatif deskriptif dengan dua instrumen standar: System Usability Scale (SUS) untuk mengukur usability dan User Experience Questionnaire (UEQ) untuk mengukur user experience pada enam dimensi. Teknik total sampling diterapkan dengan melibatkan seluruh 33 pengguna aktif yang terdiri dari petugas administrasi, perawat, bidan, dan tenaga medis. Hasil SUS menunjukkan skor rata-rata 64,39 (kategori OK/Acceptable). Hasil UEQ menunjukkan seluruh enam dimensi berada pada kategori Baik: Attractiveness (1,37), Perspicuity (1,37), Novelty (1,34), Dependability (1,33), Efficiency (1,29), dan Stimulation (1,27). Penelitian merekomendasikan penyederhanaan navigasi, optimasi server, fitur auto-save, perpanjangan sesi aktif, serta pembaruan desain antarmuka.
Generator Soal Cerita Kurikulum Matematika Dasar Berbasis Large Language Model Rohadi, Jalmo; Prasetya, Agung; Ansor, Mohamad Khoirul
HORIZON: Indonesian Journal of Multidisciplinary Vol. 4 No. 4 (2026): HORIZON: Indonesian Journal of Multidisciplinary
Publisher : Lembaga Intelektual Muda (LIM) Maluku

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54373/hijm.v4i4.7369

Abstract

Math word problems (MWPs) are essential for developing the reasoning skills of elementary school students; however, manual creation is time-consuming and results in limited problem variety. This study aims to design, implement, and evaluate a Large Language Model (LLM)-based math word problem generator that aligns with the Kurikulum Merdeka (Independent Curriculum) and produces valid, solvable problems in Indonesian. The system was developed using LLaMA 3.2 3B Instruct via QLoRA fine-tuning with 4-bit NormalFloat quantization, trained on a dataset of 3,185 entries covering 19 topics and 6 grade levels. The system generated 385 problems across 77 grade-topic combinations and was evaluated against a sample of 95 problems through assessments by three elementary school teachers and the G-Eval metric. Evaluation results indicate that 93 out of 95 problems met validity criteria (97.89%), with an average quality score of 4.95 out of 5.00. A comparison of the two evaluation methods revealed a Pearson correlation of 0.94 and a Cohen’s Kappa of 1.00. These findings demonstrate the system's potential as a tool to assist teachers in generating math word problems that align with the Kurikulum Merdeka.
Integrasi Large Language Model Dalam Automasi Penilaian Esai Pada Sistem Learning Manajemen System Mohamad Khoirul Ansor; Taufiq Agung Cahyono; Cikal Dwidyanto
Journal of Information System and Computer Vol. 6 No. 1 (2026): Juli 2026
Publisher : Universitas Islam Nahdlatul Ulama Jepara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34001/jister.v6i1.2015

Abstract

Penilaian esai secara manual pada platform Learning Management System (LMS) di perguruan tinggi Indonesia masih menghadapi tantangan berupa tingginya beban kerja dosen, inkonsistensi penilaian, dan lambatnya pemberian umpan balik. Penelitian ini bertujuan mengembangkan Learning Management System (LMS) yang terintegrasi dengan Large Language Model (LLM) untuk penilaian esai otomatis dengan pendekatan human-in-the-loop. Metode yang digunakan adalah Research and Development (R&D) dengan pengembangan Agile menggunakan framework Laravel dan model Gemma 3 12B yang dihost pada server GPU cloud melalui LM Studio Server. Sistem mengevaluasi esai berdasarkan tujuh aspek: Relevance, Content, Organization, Vocabulary, Style, Clarity, dan Conclusion. Pengujian pada 87 esai mahasiswa dengan panjang hingga 1.000 kata menunjukkan agreement rate sebesar 85% dengan empat dosen ahli, dengan rata-rata waktu pemrosesan 3,65 detik per esai. Sistem berhasil menghasilkan umpan balik yang koheren dalam Bahasa Indonesia. Survei kepuasan pengguna dengan 34 responden menghasilkan skor rata-rata tertimbang 4,23. Sistem terbukti layak sebagai alat pendukung asesmen yang efisien dan andal secara linguistik, dengan tetap mengedepankan validitas pedagogis melalui mekanisme human review.
Co-Authors Agung Prasetya Agung Prasetya Ahmad Rofi Rizaqi Cikal Dwidyanto Cikal Dwidyanto Darel Trescanaya Dea Preciosa Santyana Putri Dewi, Alivia Prasetya Fahrur Rozi Fahrur Rozi Fahrur Rozi Feri Andriawan Saputra Iskandar, Joko Kartika, Yayak Mochamad Affan Sabilla Firdos Mochammad Ilham Aldi Wahyudi Rafif Mallow Dwi Syamsoe Rohadi, Jalmo Rohmat Turnandhi Sari, Yayak Kartika Syafi', Faiza Syahrul Fajar Laqsono Sya’bana, Malfiana Rizqina Luthfillah Taufiq Agung Cahyono Turnandhi, Rohmat