Claim Missing Document
Check
Articles

Found 16 Documents
Search

ANALISIS SENTIMEN PADA TREN OPINI PUBLIK TERHADAP PROGRAM #MAKANBERGIZIGRATIS DI PLATFORM X MENGGUNAKAN JARINGAN LONG SHORT-TERM MEMORY (LSTM) Veny Dwi Wahyuningsih; Yayak Kartika Sari; Agung Prasetya
Smatika Jurnal : STIKI Informatika Jurnal Vol 16 No 01 (2026): SMATIKA Jurnal : STIKI Informatika Jurnal
Publisher : LPPM Universitas Bhinneka Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v16i01.2260

Abstract

The implementation of the Free Nutritious Meal Program (Makan Bergizi Gratis/MBG) as a strategic government initiative has generated diverse responses from the public, widely discussed on social media, particularly on the X (Twitter) platform. Differences in perceptions regarding the objectives, implementation, and impacts of the policy have encouraged intensive public discussions. However, the tendency of public sentiment toward this program has not been widely analyzed systematically using machine learning approaches based on contextual representations. Therefore, this study analyzes public sentiment toward the hashtag #MakanBergiziGratis using the Long Short-Term Memory (LSTM) method. A total of 5,516 Indonesian-language tweets were collected through a web scraping process within the period of January 1 to November 30, 2025. Sentiment labeling employed a lexicon-based approach to classify the data into three categories: positive, neutral, and negative. The analysis stages included text preprocessing, BERT tokenization and embedding, handling imbalanced data using the Synthetic Minority Over-sampling Technique (SMOTE), and sentiment classification using LSTM. The results reveal that neutral sentiment dominates with 60.80%, followed by positive sentiment at 34.34% and negative sentiment at 4.86%. The developed model achieved an accuracy of 82.50% with a weighted F1-score of 82.66%. Furthermore, evaluation using 5-fold cross-validation produced an average accuracy of 82.8%, indicating stable model performance and good generalization capability in identifying public opinion trends toward the MBG policy.
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.
THE APPLICATION OF THE MULTI-OBJECTIVE OPTIMIZATION ON THE BASIS OF SIMPLE RATIO ANALYSIS METHOD IN A DECISION SUPPORT SYSTEM FOR PROSPECTIVE UBT STUDENT ASSOCIATION CHAIR CANDIDATES Awang Pradana; Arif Fadllullah; Agung Prasetya; Fadliansyah Fadliansyah
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 2 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i2.8227

Abstract

Decision Support Systems (DSS) have become essential tools in the de-cision-making process across various fields. In the context of selecting the chairman of the Computer Engineering Student Association at Uni-versitas Borneo Tarakan, the use of DSS is also highly relevant and beneficial. The MOOSRA (Multi-Objective Optimization on the basis of Ratio Analysis) method has been chosen as the approach to implement this decision support system. This study aims to apply the MOOSRA method in the implementation of a web-based decision support system for the selection of prospective chairpersons of the Computer Engineer-ing Student Association at Universitas Borneo Tarakan. The MOOSRA method is utilized to consider several criteria, such as leadership skills, communication abilities, dedication, and organizational experience. In this research, the use of MOOSRA is combined with web technology to enhance the efficiency and quality of the candidate selection process. The MOOSRA method offers a structured and objective approach to evaluating candidates for the chairmanship. This approach involves ratio analysis and multi-objective optimization to produce better out-comes. The results of this study are expected to facilitate a fairer and more objective selection process, as well as to improve student satisfac-tion within the Computer Engineering Student Association at Universi-tas Borneo Tarakan.
Error Checker Berbasis Neural Network pada Pembentukan Soal Cerita Matematika Dasar Ferri Nurdiansah; Agung Prasetya; Taufiq Agung Cahyono
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.v4i3.316

Abstract

Soal cerita matematika (Math Word Problem/MWP) berperan penting dalam melatih kemampuan penalaran logis siswa Sekolah Dasar. Perkembangan Large Language Model (LLM) telah memungkinkan pembuatan soal secara otomatis, namun soal yang dihasilkan kerap mengandung berbagai jenis kesalahan. Penelitian ini bertujuan: (1) mengembangkan dataset MWP berbahasa Indonesia beranotasi 11 kategori kesalahan secara multi-label; (2) merancang model multi-label classification berbasis IndoBERT dan Feed Forward Neural Network (FFNN) untuk mendeteksi kesalahan secara simultan; serta (3) mengevaluasi kinerja model menggunakan metrik Micro F1-Score, Macro F1-Score, dan Hamming Loss. Dataset dikembangkan melalui error-inducing prompting, menghasilkan 2.517 soal cerita yang dianotasi secara manual oleh dua anotator dengan rasio pembagian 80:20 menggunakan stratified random sampling. Model dilatih selama 40 epoch dengan Binary Cross Entropy loss dan optimizer AdamW. Model optimal diperoleh pada epoch ke-13 dengan validation loss 0,2616. Evaluasi pada testing set menghasilkan Micro F1-Score sebesar 0,7657, Macro F1-Score sebesar 0,7631, dan Hamming Loss sebesar 0,1387. Topic Unsafety mencapai F1-Score sempurna (1,000) dan Misspellings mendekati sempurna (0,986), sementara Grade Mismatch menjadi kategori paling sulit dideteksi (F1 = 0,591). Penelitian ini menyimpulkan bahwa pendekatan multi-label classification berbasis IndoBERT efektif untuk deteksi error pada MWP berbahasa Indonesia.
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.
Pengembangan Sistem Informasi Sekolah Berbasis Website Menggunakan Metode Rapid Application Development (RAD) Tika Dwi Untari; Taufiq Agung Cahyono; Agung Prasetya
Journal of Information Technology, Software Engineering and Computer Science (ITSECS) Vol. 4 No. 4 (2026): Volume 4 Number 4 October 2026
Publisher : PT. Tech Cart Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/itsecs.v4i4.386

Abstract

Penelitian ini berfokus pada pengembangan Sistem Informasi Sekolah berbasis website di SMP Negeri 1 Gandusari yang bertujuan untuk meningkatkan efektivitas dan efisiensi pengelolaan layanan akademik dan informasi sekolah. Permasalahan yang dihadapi sebelumnya meliputi pencatatan absensi dan jurnal pembelajaran yang masih dilakukan secara manual, pengelolaan jadwal pelajaran dan jadwal mengajar yang belum terintegrasi, serta penyampaian informasi sekolah yang masih menggunakan media konvensional sehingga berpotensi menyebabkan keterlambatan informasi, duplikasi data, dan kurang efektifnya pengelolaan layanan. Metode yang digunakan adalah Rapid Application Development (RAD) dengan tahapan Requirement Planning, User Design, Construction, dan Cutover, sedangkan pengumpulan data dilakukan melalui observasi, wawancara, dan studi pustaka untuk mengidentifikasi dan memastikan kesesuaian sistem dengan kebutuhan pengguna. Hasil penelitian menunjukkan bahwa sistem yang dikembangkan mampu mengintegrasikan fitur jurnal pembelajaran beserta absensi siswa, jadwal pelajaran, jadwal mengajar guru, pendaftaran ekstrakurikuler, layanan aduan siswa, pengumuman, galeri kegiatan sekolah, serta penyampaian informasi sekolah dalam satu platform berbasis website. Pengujian menggunakan Black Box Testing menunjukkan bahwa fungsi-fungsi yang dikembangkan dapat berjalan sesuai dengan spesifikasi. Hasil evaluasi terhadap 23 responden memperoleh persentase sebesar 85,74% dengan kategori sangat baik, yang menunjukkan tingkat penerimaan dan kemudahan penggunaan sistem oleh pengguna. Dengan demikian, sistem yang dikembangkan dapat memenuhi kebutuhan pengguna dan mendukung pengelolaan layanan akademik serta informasi sekolah secara lebih efektif, efisien, terstruktur, dan mudah diakses.