Article Per Year (5 Year)
p-Index From 2021 - 2026
3.624
P-Index
This Author published in this journals
All Journal Jurnal Nasional Komputasi dan Teknologi Informasi Specta Journal of Technology Jurnal Repositor KLIK: Kajian Ilmiah Informatika dan Komputer Jurnal Informatika Teknologi dan Sains (Jinteks) Jurnal Teknologi Informasi Cyberku Jurnal Ilmu Komputer Riau Jurnal Teknik Informatika Jurnal Nasional Komputasi dan Teknologi Informasi
Alter Lasarudin
Universitas Muhammadiyah Gorontalo, Gorontalo
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Neuroscience Transportation

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
SISTEM INFORMASI PENCARIAN JASA TUKANG BANGUNAN Polapa, Risman; Abas, Mohamad Ilyas; Handayani, Tri Pratiwi; Lasarudin, Alter
Jurnal Ilmu Komputer (JUIK) Vol 4, No 3 (2024): October 2024
Publisher : Universitas Muhammadiyah Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31314/juik.v4i3.3477

Abstract

This research aims to design a Web-based Building Services Search Information System and implement a Web-Based Building Builder Services Search Information System. This research was developed using the Rapid Application Development (RAD) method. In RAD, users and analysts participate in three stages. The three stages are implementation, RAD design and requirements planning. With these stages, the application of the RAD method is very appropriate and suitable for developing website-based systems. The results of this research were that the researcher had previously conducted an interview with one of the head builders. Craftsmen in their profession as builders are to get work that suits their skills, only certain people know and understand the workman's performance, what field the craftsman is skilled in, so if there is a special job that must be done by a craftsman that suits his skills. So the employer must meet the craftsman directly and ask about the craftsman's skills. Conclusion: We have succeeded in designing a web-based information system for searching for construction services, able to make it easier for customers (employers) to search for construction services according to the skills required by customers (employers), as well as making it easier for builders to find work that suits the craftsman's skills. With this information system, it can help builders and customers (employers) in the process of searching for builders according to their expertise in the form of the Web or other web browsers.
PENERAPAN DATA MINING DALA MENGKLASIFIKASI RESIKO PENYAKIT STROKE MENGGUNAKAN METODE MACHINE LEARNING Bakari, Sitti Nurfatimah; Lasarudin, Alter; Hasyim, Wahyudin
Jurnal Ilmu Komputer (JUIK) Vol 5, No 2 (2025): JUNE 2025
Publisher : Universitas Muhammadiyah Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31314/juik.v5i2.4186

Abstract

Stroke adalah kondisi saraf yang ditandai dengan tanda klinis yang berkembang pesat, termasuk gangguan saraf lokal dan global yang parah, bertahan selama 24 jam atau lebih, dan berakibat fatal ketika tidak ada penyebab yang jelas selain vaskular. Penelitian ini bertujuan untuk menerapkan algoritma Support Vector Machine (SVM) dan Artiticial Neural Network (ANN) untuk mengklasifikasi risiko penyakit stroke dan mengukur tingkat akurasi dari masing-masing algoritma. Hasil penelitian menggunakan algoritma Support Vector Machine dan Artiticial Neural Network dengan jumlah record data 200 maka akan diperoleh nilai akurasi Support Vector Machine sebesar 97.46%, dan tingkat akurasi Artiticial Neural Network sebesar 98.75%. Paling algoritma Artificial Neural Network mendapatkan nilai akurasi yang tertinggi dibandingkan algoritma Support Vector Machine dalam pengklasifikasian data risiko penyakit stroke.
PENERAPAN DATA MINING UNTUK PREDIKSI PENJUALAN PRODUK TERLARIS MENGGUNAKAN METODE ANN DAN LSTM Hasanah, Ika Nur; Lasarudin, Alter; Hasyim, Wahyudin
Jurnal Ilmu Komputer (JUIK) Vol 5, No 2 (2025): JUNE 2025
Publisher : Universitas Muhammadiyah Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31314/juik.v5i2.4180

Abstract

Toko Setia Keramik yang menjual berbagai jenis keramik sedang menghadapi tantangan dalam menentukan produk keramik terlaris akibat data penjualan yang belum diolah secara optimal. Penelitian ini bertujuan untuk menerapkan algoritma Artificial Neural Network (ANN) dan Long Short-Term Memory (LSTM) untuk memprediksi penjualan produk keramik terlaris serta mengukur tingkat akurasi prediksi masing-masing algoritma. Data yang digunakan mencakup penjualan lima jenis keramik selama tiga tahun (2021–2023). Hasil penelitian menunjukkan bahwa algoritma ANN memberikan prediksi terbaik untuk pola jangka pendek dengan tingkat kesalahan Mean Square Error (MSE) yang rendah, sementara algoritma LSTM unggul dalam memprediksi pola jangka panjang. Penerapan kedua algoritma ini mampu membantu Toko Setia Keramik dalam menentukan jenis keramik terlaris sehingga pengelola toko dapat mengelola stok barang secara lebih efisien dan meminimalisir kekurangan maupun kelebihan stok, serta mengantisipasi tren penjualan di masa depan. Dengan demikian, penelitian ini memberikan kontribusi penting dalam optimalisasi manajemen penjualan menggunakan metode prediksi berbasis data mining.
Optimasi Data Rekam Medis Pasien Rawat Inap BPJS RSUD Tombulilato dengan Algoritma K-Means dan FP-Growth Fatiya Ointu; Alter Lasarudin; Wahyudin Hasyim
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 8, No 4 (2025): Agustus 2025
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v8i4.9348

Abstract

Abstrak - Pengelolaan data rekam medis, terutama dalam meningkatkan kualitas layanan rumah sakit di era digital, menjadi komponen yang semakin penting. Penelitian ini bertujuan untuk mengoptimalkan pengelolaan data rekam medis pasien rawat inap BPJS di Rumah Sakit Umum Daerah Tombulilato dengan menerapkan algoritma K-Means untuk clustering dan analisis pola asosiasi menggunakan algoritma FP-Growth. Hasil penelitian menunjukkan bahwa Cluster 0 terdiri dari pasien perempuan di Kelas Rawat 3, berusia dewasa (18-64 tahun), yang mengalami penyakit infeksi (dukungan 16,4% dengan kepercayaan 100%), penyakit pernapasan (dukungan 7,1% dengan kepercayaan 100%), dan komplikasi kehamilan (dukungan 11,6% dengan kepercayaan 100%). Sementara itu, Cluster 1 terdiri dari pasien laki-laki di Kelas Rawat 3, berusia dewasa (18-64 tahun), yang mengalami penyakit infeksi (dukungan 13,6% dengan kepercayaan 100%), penyakit pernapasan (dukungan 16,2% dengan kepercayaan 100%), dan penyakit mental (dukungan 10,3% dengan kepercayaan 100%).Kata kunci: FP-Growth; K-Means; Rekam Medis; Abstract - It is becoming increasingly crucial to manage medical record data in order to enhance the quality of hospital services in the digital era. This study aims to optimize the management of medical record data for BPJS inpatients at Tombulilato Regional General Hospital by applying the K-Means algorithm for clustering and association pattern analysis using the FP-Growth algorithm. The results showed that Cluster 0 consisted of female patients in Class 3, adults (18-64 years), who experienced infectious diseases (16.4% support with 100% confidence), respiratory diseases (7.1% support with 100% confidence), and pregnancy complications (11.6% support with 100% confidence). Cluster 1 was composed of male patients in Class 3, adults aged 18-64 years, who had been diagnosed with infectious diseases (13.6% support with 100% confidence), respiratory diseases (16.2% support with 100% confidence), and mental illness (10.3% support with 100% confidence).Keywords: FP-Growth; Medical Records; K-Means;
Analisis Sentimen Terhadap Kebijakan Efisisensi Anggaran Pemerintah Menggunakan Metode Support Vector Machine (SVM) Dan Vector Space Model (VSM) Dwi Fanti Utina; Alter Lasarudin; Wahyudin Hasyim
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 2 (2026): April, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/twjsnn25

Abstract

Abstrak - Media sosial saat ini menjadi wadah utama bagi masyarakat dalam menyuarakan aspirasi terhadap kebijakan pemerintah secara terbuka, termasuk isu kebijakan efisiensi anggaran. Penelitian ini bertujuan menganalisis kecenderungan sentimen publik terhadap kebijakan pemerintah menggunakan algoritma Support Vector Machine (SVM) yang diintegrasikan dengan Vector Space Model (VSM). Data dikumpulkan melalui teknik crawling pada platform X (Twitter), kemudian diproses melalui tahapan cleaning, case folding, tokenizing, filtering, dan stemming. Penelitian ini juga menerapkan pendekatan Lexicon-Based untuk pelabelan sentimen. Seluruh implementasi sistem dikembangkan menggunakan bahasa Python pada Google Colaboratory. Hasil pengujian dengan confusion matrix menunjukkan bahwa model mampu mengklasifikasikan data berlabel mandiri dengan akurasi 71%, dan mencapai 96% pada data berlabel Lexicon-Based Approach. Hal ini membuktikan integrasi VSM sangat membantu SVM dalam menyajikan representasi fitur dan mengenali pola teks secara akurat. Penelitian ini menyimpulkan bahwa persepsi masyarakat dapat dipetakan secara objektif melalui analisis sentimen, sehingga dapat menjadi bahan evaluasi dan referensi strategis bagi pemerintah dalam mengambil kebijakan di masa depan. Kata Kunci: Analisis Sentimen; Support Vector Machine; Efisiensi Anggaran; X (Twitter); Vector Space Model;   Abstract - Social media is currently the primary platform for the public to openly voice their concerns about government policies, including issues of budget efficiency. This study aims to analyze public sentiment trends toward government policies using the Support Vector Machine (SVM) algorithm integrated with the Vector Space Model (VSM). Data was collected through crawling techniques on the X (Twitter) platform, then processed through cleaning, case folding, tokenizing, filtering, and stemming. This study also applied a Lexicon-Based approach for sentiment labeling. The entire system implementation was developed using Python on Google Collaboratory. Test results using a confusion matrix showed that the model was able to classify self-labeled data with 71% accuracy and achieved 96% accuracy on data labeled with the Lexicon-Based Approach. This demonstrates that the VSM integration significantly assists the SVM in presenting feature representations and accurately recognizing text patterns. This study concludes that public perception can be objectively mapped through sentiment analysis, thus serving as evaluation material and a strategic reference for the government in future policymaking.                                                                                                     Keywords: Sentiment Analysis; Support Vector Machine; Budget Efficiency; X (Twitter); Vector Space Model;
Penerapan Algoritma Extrame Gradient Boosting (XGBoost) untuk Menganalisis Kualitas Pelayanan Kesehatan Terhadap Kepuasan Pasien di Pueskesmas Mootilango Rindiyani Saputri Agu; Wahyudin Hasyim; Alter Lasarudin
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 2 (2026): April, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/g69g4z25

Abstract

Abstrak - Pengelolaan data kepuasan pasien menjadi komponens yang semakin penting dalam meningkatkan kualitas pelayanan kesehatan di era digital. Penelitian ini bertujuan untuk mengklasifikasikan tingkat kepuasan pasien di Puskesmas Mootilango dengan menerapkan algoritma Extreme Gradient Boosting (XGBoost) berbasis dimensi SERVQUAL. Tahapan penelitian dimulai dari pengumpulan data kuesioner, preprocessing, hingga implementasi model melalui optimasi Gradient dan Hessian. Transparansi logika algoritma divalidasi secara manual melalui perhitungan nilai Similarity Score dan Gain. Hasil penelitian menunjukkan bahwa model XGBoost memiliki performa andal dengan tingkat akurasi sebesar 80,00% dan recall sebesar 88%. Analisis Feature Importance mengidentifikasi bahwa indikator Q5 (Tata Letak Ruangan) dari dimensi Tangibles dan Q8 (Keakuratan Diagnosa) dari dimensi Reliability merupakan faktor paling berpengaruh terhadap kepuasan pasien. Simulasi manual pada indikator Q5 menghasilkan nilai Total Gain sebesar 0,7238, yang membuktikan kontribusi signifikan fitur tersebut dalam meningkatkan kemurnian klasifikasi. Disimpulkan bahwa algoritma XGBoost efektif memberikan rekomendasi strategis bagi manajemen untuk memprioritaskan perbaikan pada aspek fisik dan keandalan medis demi optimalisasi kualitas pelayanan. Kata kunci : Kepuasan Pasien; XGBoost; SERVQUAL; Machine Learning; Feature Importance;   Abstract -Patient satisfaction data management is becoming an increasingly important component in improving the quality of healthcare services in the digital era. This study aims to classify patient satisfaction levels at the Mootilango Community Health Center by applying the Extreme Gradient Boosting (XGBoost) algorithm based on the SERVQUAL dimension. The research stages start from questionnaire data collection, preprocessing, to model implementation through Gradient and Hessian optimization. The transparency of the algorithm logic is manually validated by calculating the Similarity Score and Gain values. The results show that the XGBoost model has reliable performance with an accuracy rate of 80.00% and a recall of 88%. Feature Importance analysis identified that indicator Q5 (Room Layout) from the Tangibles dimension and Q8 (Diagnostic Accuracy) from the Reliability dimension are the most influential factors on patient satisfaction. Manual simulation on indicator Q5 produced a Total Gain value of 0.7238, which proves the significant contribution of this feature in improving the purity of the classification. It was concluded that the XGBoost algorithm effectively provides strategic recommendations for management to prioritize improvements in physical aspects and medical reliability to optimize service quality. Keywords: Patient Satisfaction; XGBoost; SERVQUAL; Machine Learning; Feature Importance;
Perbandingan Algoritma FP-Growth dan Apriori untuk Menganalisis Pola Pembelian Konsumen Noviyanti Patak Lembang; Alter Lasarudin; Wahyudin Hasyim
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 2 (2026): April, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/n5gaj075

Abstract

Abstrak - Pemamfaatan data transaksi penjualan berperan penting dalam mengungkap pola pembelian konsumen yang mendukung pengambilan keputusan usaha, namun pada praktiknya masih belum dimanfaatkan secara optimal oleh Usaha Kecil dan Menengah. Penelitian ini bertujuan untuk menerapkan serta membandingkan algoritma FP-Growth dan Apriori dalam menganalisis pola pembelian konsumen pada UKM Mart Koperasi Wanita Kasih Ibu. Penelitian ini menggunakan pendekatan Kuantitatif dengan teknik Association Rule Mining terhadap data transaksi penjualan periode Januari hingga Desember 2024, dengan jumlah data awal sebanyak 9305 transaksi dan setelah proses pembersihan diperoleh 7972 transaksi yang terdiri dari dua atribut. Analisis data dilakukan menggunakan aplikasi RapidMiner. Hasil penelitian menunjukkan bahwa algoritma FP-Growth menghasilkan 55 aturan asosiasi dengan waktu pemrosesan yang 1 detik, sedangkan algoritma Apriori menghasilkan 57 aturan asosiasi dengan waktu pemrosesan 4 detik. Penelitian ini menunjukkan bahwa algoritma FP-Growth lebih efektif digunakan dalam mengidentifikasi pola pembelian konsumen sebagai dasar penyusunan strategi pemasaran dan pengelolaan persediaan. Kata kunci : Data Mining; Association Rule Mining; FP-Growth; Apriori; Pola Pembelian Konsumen; Abstract - Utilization Sales transaction data plays an important role in revealing consumer purchasing patterns that support business decision-making, but in practice it is still not optimally utilized by Small and Medium Enterprise. This study aims to apply and compare the FP-Growth and Apriori algorithms in analyzing consumer purchasing pattern at UKM Mart Koperasi Wanita Kasih Ibu. This study uses a quantitative approach with the technique of Association Rule Mining the analysis used sales transaction data from January to Desember 2024, with an initial data set of 9,305 transactions and after the cleaning process, 7,972 transactions consisting of two attributes were obtained. Data analysis was performed using the RapidMiner application. The results showed that the FP-Growth algorithm generated 55 association rules with a processing time of 1 second, while the Apriori algorithm generated 57 association rules with a processing time of 4 seconds. This study indicates that the FP-Growth algorithm is more effective in identifying consumer purchasing patterns as a basic for developing marketing strategies and inventory management. Keywords: Data Mining; Association Rule Mining; FP-Growth, Apriori; Consumer Purchasing Patterns;
Klasifikasi Hard Skill dan Soft Skill IT dari Iklan Kerja Menggunakan Metode Berbasis Rule-Based dan Similarity Matching Hapsa Husain; Wahyudin Hasyim; Alter Lasarudin; Tri Pratiwi Handayani
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 3 (2026): Juni, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/pf66v794

Abstract

Abstrak - Kesenjangan kompetensi antara lulusan perguruan tinggi dengan kebutuhan aktual industri Teknologi Informasi (TI) masih menjadi kendala utama dalam penyerapan tenaga kerja. Penelitian ini bertujuan untuk mengklasifikasikan kompetensi hard skill dan soft skill yang diekstraksi dari data iklan lowongan kerja guna memetakan kebutuhan industri secara presisi. Metodologi yang diterapkan menggunakan pendekatann yang menggabungkan metode rule-based untuk ekstraksi entitas kompetensi serta similarity matching dengan algoritma Cosine Similarity untuk proses pemetaan terhadap Standar Kompetensi Kerja Nasional Indonesia (SKKNI). Penelitian ini mengolah data sebanyak 701 iklan lowongan kerja IT dengan merujuk pada 2.126 unit kompetensi SKKNI yang mencakup 57 okupasi. Hasil penelitian menunjukkan bahwa penggunaan metode Rule-Based dan Similarity Matching mampu mengidentifikasi variasi kompetensi pada teks iklan kerja yang tidak terstruktur dengan performa sangat baik, dibuktikan dengan nilai akurasi sebesar 88,02%, presisi 88,09%, recall 96,92%, dan F1-score 92,29%. Berdasarkan Hasil penelitian mengungkap dominasi kebutuhan hard skill (62.0%) dengan prioritas pada bidang keamanan siber (security) dan basis data, sementara soft skill (38,0%) didominasi oleh kemampuan komunikasi dan pemecahan masalah. Kerangka kerja ini diharapkan dapat membantu institusi pendidikan dalam sinkronisasi kurikulum serta menjadi panduan bagi pencari kerja dalam memetakan kompetensi spesifik yang dibutuhkan industri. Kata Kunci: Hard Skill; Soft Skill; IT; Rule-Based; Cosine Similarity; SKKNI; Iklan Kerja;   Abstract - The competency gap between university graduates and the actual needs of the Information Technology (IT) industry remains a major obstacle to workforce absorption. This study aims to classify hard and soft skill competencies extracted from job advertisement data to precisely map industry needs. The applied methodology uses a rule-based approach for extracting competency entities and similarity matching with the Cosine Similarity algorithm for mapping against the Indonesian National Work Competency Standards (SKKNI). This study processed data from 701 IT job advertisements, referring to 2,126 SKKNI competency units covering 57 occupations. The results of the study indicate that the Rule-Based and Similarity Matching method is capable of identifying competency variations in unstructured job advertisement text with excellent performance, as evidenced by an accuracy of 88.02%, a precision of 88.09%, a recall of 96.92%, and an F1-score of 92.29%. The results revealed a dominant need for hard skills (57.8%), with a priority on cybersecurity and databases, while soft skills (42.2%) were dominated by communication and problem-solving abilities. This framework is expected to assist educational institutions in curriculum synchronization and serve as a guide for job seekers in mapping specific competencies needed by the industry. Keywords: Hard Skills; Soft Skills; IT; Rule-Based; Cosine Similarity; SKKNI; Job Advertisements;
Analisis Penggunaan Large Language Model (LLM) dalam Proses Belajar Mahasiswa Miranda A. Hasan; Alter Lasarudin; Frangky Tupamahu
Jurnal Nasional Komputasi dan Teknologi Informasi Vol. 9 No. 3 (2026): Juni, 2026
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/bcmrjx78

Abstract

Abstrak - Penelitian ini bertujuan untuk memetakan pola penggunaan LLM, mengevaluasi tingkat efisiensi proses belajar, serta mengukur dampak kompetensi teknis prompt engineering mahasiswa terhadap validitas informasi di Universitas Muhammadiyah Gorontalo. Jenis penelitian adalah kuantitatif dengan pendekatan deskriptif. Jumlah sampel sebanyak 96 mahasiswa aktif dari berbagai tahun angkatan yang dipilih menggunakan teknik Proportionate Stratified Random Sampling. Analisis data dilakukan secara deskriptif dan perhitungan Tingkat Capaian Responden (TCR) menggunakan bantuan software SPSS. Hasil penelitian menunjukkan bahwa LLM telah menjadi bagian dari aktivitas akademik rutin mahasiswa, di mana platform yang paling dominan digunakan adalah ChatGPT (38,5%) dengan jenis tugas terbanyak adalah mencari referensi (34,5%). Dari aspek efisiensi belajar, indikator efisiensi waktu memperoleh TCR tertinggi sebesar 88% (Kategori Baik/Efisien), sementara indikator beban verifikasi memperoleh skor terendah sebesar 74% (Kategori Cukup). Pada variabel prompt engineering dan risiko halusinasi, aspek validasi output meraih TCR tertinggi sebesar 78,48%, sedangkan kesadaran risiko halusinasi berada pada angka 73,89%. Dapat disimpulkan bahwa penggunaan LLM dinilai efektif dalam mengakselerasi produktivitas belajar mahasiswa, namun penerapannya tetap membutuhkan sikap kritis dan verifikasi mandiri yang ketat agar hasil belajar yang diperoleh tetap valid dan akurat Kata kunci : Large Language Model; Efisiensi Belajar; UTAUT; Prompt Engineering; Hallucination Trap; Abstract – This study aims to map the patterns of LLM usage, evaluate the efficiency level of the learning process, and measure the impact of students' technical competence in prompt engineering on information validity at Universitas Muhammadiyah Gorontalo. This type of research is quantitative with a descriptive approach. The sample consisted of 96 active students from various class years selected using the Proportionate Stratified Random Sampling technique. Data analysis was conducted descriptively along with the calculation of the Respondent Achievement Level (TCR) using SPSS software. The results showed that LLMs have become a part of students' routine academic activities, where the most dominant platform used is ChatGPT (38.5%) and the most frequent type of academic task assisted is searching for references (34.5%). From the aspect of learning efficiency, the time efficiency indicator obtained the highest TCR of 88% (Good/Efficient Category), while the verification burden indicator obtained the lowest score of 74% (Sufficient Category). In the prompt engineering and hallucination risk variables, the output validation aspect achieved the highest TCR of 78.48%, while the awareness of hallucination risk stood at 73.89%. It can be concluded that the use of LLMs is considered effective in accelerating student learning productivity, yet its application still requires strict critical thinking and independent verification to ensure that the learning outcomes obtained remain valid and accurate. Keywords: Large Language Model; Learning Efficiency; UTAUT; Prompt Engineering; Hallucination Trap;
Sistem Pendukung Keputusan Reward Penyidik Terbaik Berbasis Web Menggunakan AHP-SAW Ivone Djafar; Hilmansyah Gani; Alter Lasarudin; Wahyudin Hasyim
Riau Jurnal Teknik Informatika Vol. 5 No. 2 (2026): Juli 2026
Publisher : Prodi Teknik Informatika Universitas Pasir Pengaraian

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30606/rjti.v5i2.4710

Abstract

The investigator reward process at the Narcotics Investigation Directorate of Gorontalo Regional Police is still conducted manually, making it prone to subjectivity, inconsistency, and time-consuming evaluations. This study aims to develop a web-based Decision Support System (DSS) for selecting the best investigator using the Analytical Hierarchy Process (AHP) and Simple Additive Weighting (SAW) methods. The system was developed using the Rapid Application Development (RAD) approach and evaluated 20 investigator alternatives based on five criteria: Electronic Management of Investigators (EMP), Case Resolution, Discipline, Integrity, and Teamwork. The AHP method was applied to determine the priority weights of the evaluation criteria, while the SAW method was used to calculate preference values and rank the alternatives. The results show that Electronic Management of Investigators (EMP) is the most influential criterion with a weight of 41.62%, while alternative A2 achieved the highest preference value of 0.8923, making it the recommended best investigator. The developed system successfully automates the weighting, ranking, and reporting processes, thereby supporting a more objective, transparent, and measurable decision-making process. The novelty of this study lies in the development of a web-based DSS that integrates administrative and behavioral performance indicators into a single evaluation model for investigator reward selection, providing a more comprehensive assessment than conventional evaluation approaches.
Co-Authors Arifin Ahudulu Bagus Setio Raharjo Bakari, Sitti Nurfatimah Citra Ayu Djainab Humolungo Dwi Fanti Utina Fahriyadi Purnama Thaib Fatiya Ointu Frangky Tupamahu Gani, Hilmansyah Handayani, Tri Pratiwi Hapsa Husain Hasanah, Ika Nur Ibrahim, Irawan Ivone Djafar Miranda A. Hasan Misran Tomayahu Mohamad Ilyas Abas Natalia R Simon Noviyanti Patak Lembang Polapa, Risman Purwanto Purwanto Rindiyani Saputri Agu Roy Dumako Rubiyanto Maku Sitnasanti Yane Tri Pratiwi Handayani Wahyudin Hasyim Yulanda Yunus