Search Articles & Publications

Showing 82 articles found for "Enhances"

OPTIMIZING RETRIEVAL-AUGMENTED GENERATION FOR DOMAIN-SPECIFIC KNOWLEDGE SYSTEMS THROUGH FINE-TUNING AND PROMPT ENGINEERING

Ahmad Fajri, Rila Mandala
Abstract: Abstract: This study discusses the optimization of RAG for a FAQ system in the field of information technology product security certification at BSSN. Although LLM generate reliable responses, they often lack up-to-date… and domain-specific knowledge, which can be addressed through the RAG approach. This research aims to optimize a domain-specific RAG system by improving embedding performance, enhancing prompt robustness, and increasing retrieval accuracy. The research methods consist of three stages. The first stage involves fine-tuning the bge-m3 embedding model and evaluating its performance using MRR, Recall, and AUC. The second stage applies prompt engineering techniques, namely the SRSM and Autodefense, to mitigate direct-injection and escape-character prompt injection attacks. The third stage evaluates the proposed RAG system using Precision, Recall, and F1-Score metrics against four baseline models. The results of research show that the fine-tuned embedding model achieves higher performance than the original model, with MRR@1 and Recall@1 values of 0.80 and an AUC@100 of 0.7023. In addition, the proposed prompt engineering techniques demonstrate robustness against prompt injection attacks, while the overall RAG system attains a perfect Precision, Recall, and F1-Score of 1.00. In conclusion, the proposed approach effectively enhances retrieval accuracy, embedding quality, and system security, resulting in a more reliable RAG-based FAQ system for information technology product security certification. Keywords: embedding fine-tuning; large language model; prompt engineering; prompt injection mitigation; retrieval-augmented generation   Abstrak: Studi ini membahas optimasi RAG untuk sistem FAQ di bidang sertifikasi keamanan produk teknologi informasi di BSSN. Meskipun LLM menghasilkan respons yang andal, mereka seringkali kurang memiliki pengetahuan terkini dan spesifik domain, yang dapat diatasi melalui pendekatan RAG. Penelitian ini bertujuan untuk mengoptimalkan sistem RAG spesifik domain dengan meningkatkan kinerja embedding, meningkatkan ketahanan prompt dan meningkatkan akurasi pengambilan. Metode penelitian terdiri dari tiga tahap. Tahap pertama melibatkan fine-tuning model embedding bge-m3 dan mengevaluasi kinerjanya menggunakan Mean Reciprocal Rank (MRR), Recall, dan AUC. Tahap kedua menerapkan teknik rekayasa prompt, yaitu Self- SRSM dan Autodefense, untuk mengurangi serangan direct-injection dan escape-character prompt injection. Tahap ketiga mengevaluasi sistem RAG yang diusulkan menggunakan metrik Presisi, Recall, dan F1-Score terhadap empat model dasar. Hasil penelitian menunjukkan bahwa model embedding yang disempurnakan mencapai kinerja yang lebih tinggi daripada model asli, dengan nilai MRR@1 dan Recall@1 sebesar 0,80 dan AUC@100 sebesar 0,7023. Selain itu, teknik rekayasa prompt yang diusulkan menunjukkan ketahanan terhadap serangan injeksi prompt, sementara sistem RAG secara keseluruhan mencapai Presisi, Recall, dan F1-Score sempurna sebesar 1,00. Kesimpulannya, pendekatan yang diusulkan secara efektif meningkatkan akurasi pengambilan, kualitas embedding dan keamanan sistem, menghasilkan sistem FAQ berbasis RAG yang lebih andal untuk sertifikasi keamanan produk teknologi informasi. Kata kunci: penyempurnaan embedding; model bahasa besar; rekayasa prompt; mitigasi injeksi prompt; retrieval-augmented generation

WEB-BASED INVENTORY SYSTEM DEVELOPMENT WITH AGILE AT CV DAZRY HARAPAN

Saputra, Muhammad Hadi, Dristyan, Febri, Handoko, Dedi
Abstract: Abstract: Dazry Harapan Household Industry (IRT) is an SME in Jambi City specializing in the production of laundry perfume and previously relied on manual record-keeping using notebooks. This conventional method created… several issues, including frequent stock recording errors, difficulties in preparing financial reports, delays in identifying minimum stock levels, and the absence of structured historical data. This study aims to develop a web-based digital recording system to improve efficiency, accuracy, and transparency in inventory management. The system was developed using the Agile (Scrum) methodology through three sprints covering the creation of login modules, stock and transaction recording, reporting, minimum-stock notifications, and interface refinement. System design was formulated using use case diagrams, flowcharts, database modeling, and interface prototypes based on the Laravel framework. User Acceptance Testing (UAT) demonstrated high user satisfaction, with 90% of respondents stating that the system is easy to use, 85% reporting faster administrative processes, and 95% acknowledging improved reporting accuracy. The system also increased recording efficiency by 66%—from 3 minutes to 1 minute per transaction—and reduced stock recording errors from 15% to 2% per month. The results indicate that implementing a web-based digital recording system significantly enhances the operational performance of SMEs.             Keywords: SMEs, digital recording system, Agile, inventory management, Laravel.   Abstrak: Industri Rumah Tangga (IRT) Dazry Harapan merupakan UMKM di Kota Jambi yang bergerak pada produksi parfum laundry dan masih menggunakan sistem pencatatan manual berbasis buku tulis. Metode konvensional tersebut menimbulkan berbagai permasalahan, seperti tingginya kesalahan pencatatan stok, hambatan dalam penyusunan laporan keuangan, keterlambatan identifikasi stok minimum, serta ketiadaan rekap data historis yang terstruktur. Penelitian ini bertujuan mengembangkan sistem pencatatan digital berbasis web untuk meningkatkan efisiensi, akurasi, dan transparansi manajemen persediaan. Pengembangan dilakukan menggunakan metode Agile (Scrum) melalui tiga sprint yang mencakup pembangunan modul login, pencatatan stok, transaksi, laporan, notifikasi stok minimum, serta penyempurnaan antarmuka. Desain sistem dirumuskan menggunakan use case diagram, flowchart, perancangan database, dan prototipe antarmuka berbasis Laravel. Hasil pengujian melalui User Acceptance Test (UAT) menunjukkan tingkat penerimaan pengguna yang tinggi, yaitu 90% menilai sistem mudah digunakan, 85% merasakan percepatan proses pencatatan, dan 95% menilai laporan yang dihasilkan lebih akurat. Efisiensi waktu pencatatan meningkat sebesar 66%, dari 3 menit menjadi 1 menit per transaksi, sedangkan tingkat kesalahan pencatatan menurun dari 15% menjadi 2% per bulan. Penelitian ini membuktikan bahwa implementasi sistem pencatatan digital berbasis web mampu meningkatkan kualitas operasional UMKM secara signifikan.   Kata kunci: UMKM; sistem pencatatan digital; Agile; manajemen stok; Laravel;

OPTIMIZATION OF SUPPORT VECTOR MACHINE WITH SMOTE AND BAYESIAN METHOD FOR HEART FAILURE CLASSIFICATION

Doni Agung Prasetyo, Harminto Mulyo, Nadia Annisa Maori
Abstract: Abstract: This study applies an integrated approach to optimize heart failure classification. The main objective is to address the challenge of class imbalance in medical datasets and to improve the accuracy, sensitivity,… , and generalization of the classification model. The urgency of this issue is emphasized by statistics showing that cardiovascular diseases cause approximately 17.9 million deaths worldwide each year. Using a quantitative experimental approach, this study analyzes the "Heart Failure Prediction Dataset" from Kaggle, which consists of 918 records. The data were processed through normalization and encoding, followed by the application of SMOTE on the training set to balance class distribution. This step successfully increased model accuracy from 88.41% to 90.22% and minority class recall from 0.82 to 0.88. Furthermore, Bayesian Optimization was employed to refine the hyperparameters of SVM, resulting in a final model with an accuracy of 89.13% that demonstrated better generalization. This integrated approach significantly enhances the stability, sensitivity, and generalization of the model, making it a reliable tool for clinical decision support systems in predicting heart failure.   Keywords: bayesian optimization; heart failure; machine learning; SMOTE; SVM.   Abstrak: Penelitian ini menerapkan pendekatan terintegrasi untuk mengoptimalkan klasifikasi gagal jantung. Tujuan utama studi ini adalah untuk mengatasi tantangan ketidakseimbangan kelas dalam dataset medis dan meningkatkan akurasi, sensitivitas, serta generalisasi model klasifikasi. Urgensi ini ditegaskan oleh statistik yang menunjukkan bahwa penyakit kardiovaskular menyebabkan sekitar 17,9 juta kematian setiap tahun secara global. Menggunakan pendekatan eksperimental kuantitatif, penelitian ini menganalisis "Heart Failure Prediction Dataset" dari Kaggle, yang terdiri dari 918 catatan. Data diproses dengan normalisasi dan encoding, lalu SMOTE diterapkan pada data pelatihan untuk menyeimbangkan distribusi kelas. Langkah ini berhasil meningkatkan akurasi dari 88,41% menjadi 90,22% dan recall kelas minoritas dari 0,82 menjadi 0,88. Selanjutnya, Bayesian Optimization menyempurnakan hyperparameter SVM, menghasilkan model akhir dengan akurasi 89,13% yang menunjukkan generalisasi lebih baik. Pendekatan terintegrasi ini secara signifikan meningkatkan stabilitas, sensitivitas, dan generalisasi model. Hasil penelitian ini menjadikannya alat yang andal untuk sistem pendukung keputusan klinis dalam prediksi gagal jantung. Kata kunci: bayesian optimization; gagal jantung; machine learning; SMOTE; SVM

IMPLEMENTATION OF E-SCM AS A SOLUTION TO OPTIMIZE SHOE STOCK SUPPLY CHAIN IN GASTI JAYA STORE

Siregar, Sindi Fatika Sari, Sembiring, Muhammad Ardiansyah, Ananda, Ricki
Abstract: Abstract: In the retail industry, effective supply chain management is essential to ensure stock availability aligns with market demand. Gasti Jaya Store, a growing shoe retailer, faces challenges in optimizing inventory… management, often leading to stock surpluses or shortages. These issues can impact operational efficiency and customer satisfaction. To address this problem, this study the implementation of Electronic Supply Chain Management (E-SCM) as a solution to optimize supply chain management. E-SCM enables the integration of technology-based systems for real-time stock monitoring, procurement, and distribution. Using a case study method and a qualitative approach, this research evaluates the effectiveness of E-SCM in enhancing operational efficiency, reducing excess stock, and accelerating the distribution process at Gasti Jaya Store. The findings indicate that E-SCM implementation improves data transparency, speeds up decision-making, and enhances customer satisfaction. Additionally, the system helps reduce operational costs by optimizing inventory management and minimizing the risk of stock imbalances. In conclusion, the adoption of E-SCM can serve as an effective strategy for mid-sized retail businesses to improve their competitiveness and supply chain efficiency. Keywords: E-SCM; inventory stock; operational efficiency.    Abstrak: Dalam industri ritel, manajemen rantai pasok yang efektif sangat diperlukan untuk memastikan ketersediaan stok sesuai dengan permintaan pasar. Toko Gasti Jaya sebagai salah satu toko sepatu yang berkembang menghadapi tantangan dalam mengelola persediaan secara optimal, yang sering kali menyebabkan kelebihan atau kekurangan stok. Permasalahan ini dapat berdampak pada efisiensi operasional dan kepuasan pelanggan. Untuk mengatasi masalah tersebut, penelitian ini mengusulkan penerapan Electronic Supply Chain Management (E-SCM) sebagai solusi dalam mengoptimalkan manajemen rantai pasok. E-SCM memungkinkan integrasi sistem berbasis teknologi dalam proses pemantauan stok, pengadaan barang, hingga distribusi secara real-time. Dengan metode studi kasus dan pendekatan kualitatif, penelitian ini mengevaluasi efektivitas E-SCM dalam meningkatkan efisiensi operasional, mengurangi kelebihan stok, serta mempercepat proses distribusi di Toko Gasti Jaya. Hasil penelitian menunjukkan bahwa implementasi E-SCM mampu meningkatkan transparansi data, mempercepat pengambilan keputusan, dan meningkatkan kepuasan pelanggan. Selain itu, sistem ini membantu mengurangi biaya operasional dengan mengoptimalkan manajemen persediaan dan meminimalkan risiko ketidakseimbangan stok. Kesimpulannya, penerapan E-SCM dapat menjadi strategi yang efektif bagi bisnis ritel skala menengah untuk meningkatkan daya saing dan efisiensi rantai pasok mereka. Kata Kunci: E-SCM; efisiensi operasional; persediaan stok.

THE ROLE OF PERCEIVED CONVENIENCE ON WHATSAPP ADOPTION USING UTAUT2 MODEL

Winata, Kenny Calnelius, Panjaitan, Erwin Setiawan
Abstract: Abstract: Advancements in digital technology have significantly transformed communication and learning. Traditional learning methods have limitations in providing a fast and interactive learning environment, necessitating… g accessible technology that enhances student and teacher engagement while ensuring convenience. WhatsApp has emerged as a widely used solution due to its accessibility, privacy features, and cross-platform compatibility, offering users a sense of convenience. This study examines the role of Perceived Convenience in the acceptance and use of WhatsApp in secondary education in Medan City using the UTAUT2 Model. A survey was conducted with 439 respondents from 8 secondary schools in Medan and analyzed using SEM-PLS with SmartPLS-4. The results indicate that social influence, hedonic motivation, habit, and perceived convenience positively impact the intention to use WhatsApp. Additionally, facilitating conditions, perceived convenience, and intention to use significantly influence actual usage behavior. However, performance expectancy, effort expectancy, and price value do not affect either intention or behavior in using WhatsApp. Moderating variables such as age, gender, and experience partially moderate the relationships between independent factors and WhatsApp usage intention and behavior. This study contributes by incorporating Perceived Convenience into the UTAUT2 Model and affirming its role in educational technology adoption.             Keywords: perceived convenience; secondary education; UTAUT2; whatsapp     Abstrak: Kemajuan teknologi digital telah membawa perubahan signifikan dalam komunikasi dan pembelajaran. Metode pembelajaran tradisional memiliki keterbatasan dalam menyediakan lingkungan belajar yang cepat dan interaktif, sehingga diperlukan teknologi yang mudah diakses, meningkatkan keterlibatan siswa dan guru, serta nyaman digunakan. WhatsApp menjadi salah satu solusi dan banyak digunakan karena mudah diakses, privasi yang ditawarkan, serta kompatibilitas lintas platform sehingga memberikan kenyamanan yang dapat dirasakan pengguna ketika menggunakannya. Oleh karena itu, Penelitian ini menguji peran Persepsi Kenyamanan terhadap penerimaan dan penggunaan WhatsApp dalam pendidikan menengah di Kota Medan menggunakan Model UTAUT2. Survei dilakukan pada 439 responden dari 8 sekolah menengah di kota Medan, dan dianalisis dengan SEM-PLS menggunakan SmartPLS-4. Hasil penelitian menunjukkan bahwa social influence, hedonic motivation, habit, dan perceived convenience berpengaruh positif signifikan terhadap behavioral intention. Sementara itu, facilitating conditions, perceived convenience, dan behavioral intention berdampak positif pada use behavior. Namun, performance expectancy, effort expectancy, dan price value tidak berpengaruh terhadap niat maupun perilaku penggunaan WhatsApp. Variabel moderasi usia, jenis kelamin, dan pengalaman memoderasi sebagian hubungan antara faktor bebas terhadap niat dan perilaku penggunaan WhatsApp. Penelitian ini berkontribusi dengan menambahkan variabel persepsi kenyamanan (perceived convenience) ke dalam Model UTAUT2 dan menegaskan perannya dalam adopsi teknologi pendidikan.   Kata kunci: pendidikan menengah; persepsi kenyamanan; UTAUT2; whatsapp

CUSTOMER MAPPING SYSTEM WITH WEB TECHNOLOGY ON THE SIDEAK MOTOR TO IMPROVE EFFICIENCY AND ACCURACY

Nababan, Pesta Cici Dubliana, Saputra, Herman, Syahputra, Abdul Karim
Abstract: Abstract: The implementation of Geographic Information Systems (GIS) within organizations has become essential in accomplishing work activities in the modern era. Sideak Motor is a financing company in Kisaran City, Asahan… an Regency, that provides loans using motorcycle registration certificates (BPKB) as collateral, with a customer base reaching 6,052. Sideak Motor faces difficulties in data management. During meetings concerning customer locations, data communication with owners and office staff is often problematic. Additionally, when duties are transferred, new field officers struggle to locate customers because the previous officers could only provide textual information. As a result, office staff have no precise knowledge of customer locations—only the field officers do. This study aims to design a web-based customer mapping system to facilitate information storage, reduce costs, save time, and produce an information system that enhances the efficiency and accuracy of customer data management. The resulting system presents the distribution of customer locations and provides accessible information such as personal data, addresses, route details, and photos of customers’ homes, thereby simplifying the operations of Sideak Motor. Keywords: customer distribution mapping; geographic information system (GIS); sideak motor.   Abstrak: Penerapan sistem informasi geografis dalam organisasi menjadi hal utama untuk menyelesaikan suatu aktivitas pekerjaan pada era sekarang ini. Sideak Motor merupakan salah satu perusahaan pembiayaan dengan agunan BPKB sepeda motor di Kota Kisaran Kabupaten Asahan yang memiliki nasabah mencapai 6.052, Sideak Motor kesulitan dalam pengelolaan data, saat melakukan rapat mengenai lokasi nasabah sulit dilakukan komunikasi data dengan pemilik dan petugas kantor lainnya, serta pada saat pergantian tugas, petugas lainnya kesulitan mencari lokasi nasabah, karena petugas lapangan hanya bisa memberikan informasi berupa teks, dengan begitu petugas kantor tidak mengetahui lokasi pasti nasabah Sideak Motor, jadi yang mengetahui lokasi mengenai tempat tinggal nasabah hanya petugas lapangan. Penelitian ini memiliki tujuan untuk merancang sebuah sistem pemetaan nasabah berbasis web yang dapat mempermudah dalam penyimpanan informasi, mengurangi biaya, menghemat waktu serta menghasilkan sistem informasi yang dapat meningkatkan efisiensi dan akurasi pengelolaan data nasabah. Hasil sistem ini menyajikan sebaran pemetaan lokasi nasabah menyediakan informasi berupa biodata, alamat, rincian rute, dan gambar rumah nasabah yang dapat diakses secara cepat dan akurat sehingga dapat mempermudah pihak sideak motor. Kata Kunci: pemetaan sebaran nasabah; sistem informasi geografis (SIG); sideak motor

AI-BASED ALGORITHMS FOR NETWORK SECURITY: TRENDS, PER-FORMANCE, AND CHALLENGES

Marison, Sihol, Silvanus, Silvanus, Rusdiah, Rudi
Abstract: Abstract: The advancement of network security faces growing challenges as cyberattacks become more sophisticated. Traditional rule-based systems struggle with zero-day attacks and obfuscation techniques. This study examines… nes the development trends of AI-based algo-rithms, particularly machine learning and deep learning, in threat detection. A literature review evaluates AI-driven approaches, including support vector machines, random for-est, deep neural networks, convolutional neural networks, and reinforcement learning. Findings show that AI enhances detection accuracy, adaptability, and reduces false posi-tives. Machine learning efficiently classifies known attacks, while deep learning excels in identifying complex patterns such as distributed denial-of-service and advanced persis-tent threats. Unsupervised learning improves anomaly detection without labeled data. However, AI models require high-quality data, substantial computational resources, and remain vulnerable to adversarial attacks. Despite these challenges, AI provides a dynam-ic and adaptive security solution, surpassing traditional systems. Future research should enhance AI scalability and resilience for evolving cybersecurity threats.   Keywords: anomaly detection; artificial intelligence; deep learning; machine learning; network security   Abstrak: Perkembangan keamanan jaringan menghadapi tantangan yang semakin besar seiring meningkatnya kompleksitas serangan siber. Sistem berbasis aturan tradisional kesulitan mendeteksi zero-day attack dan teknik penyamaran. Penelitian ini mengkaji tren pengembangan algoritma berbasis AI, khususnya machine learning dan deep learning, dalam deteksi ancaman. Literature review mengevaluasi pendekatan berbasis AI, termasuk support vector machines, random forest, deep neural networks, convolutional neural networks, dan reinforcement learning. Hasil penelitian menunjukkan bahwa AI meningkatkan akurasi deteksi, adaptabilitas terhadap ancaman baru, serta mengurangi false positive. Machine learning efektif mengklasifikasikan serangan yang telah diketahui, sementara deep learning unggul dalam mengenali pola kompleks seperti distributed denial-of-service dan advanced persistent threats. Unsupervised learning meningkatkan deteksi anomali tanpa memerlukan data berlabel. Namun, AI masih bergantung pada data berkualitas tinggi, sumber daya komputasi besar, dan rentan terhadap adversarial attack. Meskipun demikian, AI menawarkan solusi keamanan yang lebih dinamis dan adaptif dibandingkan sistem tradisional. Penelitian selanjutnya perlu difokuskan pada peningkatan skalabilitas dan ketahanan AI dalam menghadapi ancaman siber yang terus berkembang.   Kata kunci: deteksi anomali; jaringan keamanan; kecerdasan buatan; pembelajaran dalam; pembelajaran mesin

AUTOMATIC SPEECH RECOGNITION (ASR) BASED ON PROGRESSIVE WEB APPS TO DEVELOP PRONUNCIATION LEARNING

Iqbal, Muhammad
Abstract: Abstract: Good pronunciation plays a crucial role in enhancing students' confidence, encouraging active participation in learning, and preparing them for academic and professional opportunities, such as English-language… interviews. Poor pronunciation during scholarship or job interviews can hinder the interviewer's understanding, thereby reducing the chances of acceptance. This study aims to improve students' pronunciation fluency and develop a learning medium based on Automatic Speech Recognition (ASR) technology. The method employed involves the development of Progressive Web Apps (PWA) integrated with ASR technology from the app.lumi.education platform, supported by manual labeling for pronunciation validation. The research was conducted at LKP Vijaya Learning Centre, Tanjungbalai City. The results demonstrate that ASR-based media significantly enhances students' pronunciation accuracy and confidence. Thus, the integration of ASR technology into PWA effectively supports innovative and efficient pronunciation learning.             Keywords: automatic speech recognition; language learning; pronunciation; web-based application.    Abstrak: Pengucapan yang baik berperan penting dalam meningkatkan kepercayaan diri siswa, mendorong partisipasi aktif dalam pembelajaran, dan mempersiapkan mereka menghadapi peluang akademik maupun profesional, seperti wawancara berbahasa Inggris. saat menghadapi wawancara beasiswa atau pekerjaan berbahasa Inggris, pengucapan yang buruk dapat mengurangi pemahaman pewawancara, sehingga mengurangi peluang diterima. Penelitian ini bertujuan untuk meningkatkan kelancaran pengucapan siswa dan mengembangkan media pembelajaran berbasis teknologi Automatic Speech Recognition (ASR). Metode yang digunakan adalah pengembangan Progressive Web Apps (PWA) yang terintegrasi dengan ASR dari aplikasi app.lumi.education, didukung oleh pelabelan manual untuk validasi pengucapan. Penelitian dilakukan di LKP Vijaya Learning Centre, Kota Tanjungbalai. Hasil penelitian menunjukkan bahwa media berbasis ASR secara signifikan meningkatkan akurasi pengucapan dan kepercayaan diri siswa. Dengan demikian, integrasi teknologi ASR dalam PWA terbukti mendukung pembelajaran pengucapan secara inovatif dan efisien. Kata kunci: aplikasi berbasis web; pengenalan suara otomatis; pembelajaran bahasa; pengucapan

TOWARDS SPATIAL INFORMATION SYSTEM ADOPTION USING EXTENDED TAM AND IS SUCCESS MODEL

Anjani, Heni, Inan, Dedi I., Juita, Ratna, Sanglise, Marlinda
Abstract: Abstract: By leveraging digital technology, Laporkitong enhances transparency and accountability, as well as facilitates public participation in the oversight and enforcement processes related to land use and natural resource… ource management. The Laporkitong website functions as an online reporting application aimed at documenting instances of spatial planning violations in the West Papua Province. The lack of public knowledge about the Laporkitong application has led to numerous issues. Therefore, an analysis of the adoption of the Laporkitong application is necessary. This study aims to investigate the influence of Perceived Quality, Perceived Control, and Perceived Ease of Use factors as determinants of the residents' willingness to use the Laporkitong application, employing the Technology Acceptance Model (TAM) and DeLone and McLean IS Success (IS D&M) theories. As many as 160 valid respondents are gathered based purposive sampling technique and evaluated using Partial Least Square Structural Equation Modeling (PLS-SEM). The results inform that all seven hypotheses are accepted with the R-square of the intention to use is 0.273 indicationg 27.3% variance of the model can determine the outcome. Further discussion and conclusion regarding the implication of theoretical and practical contribution are also discussed.             Keywords: laporkitong; perceived control; perceived ease of use; perceived quality; technology acceptance model   Abstrak: Dengan memanfaatkan teknologi digital, Laporkitong meningkatkan transparansi dan akuntabilitas, serta memfasilitasi partisipasi publik dalam proses pengawasan dan penegakan terkait penggunaan lahan dan pengelolaan sumber daya alam. Website Laporkitong berfungsi sebagai aplikasi pelaporan online yang bertujuan untuk mendokumentasikan pelanggaran perencanaan tata ruang di Provinsi Papua Barat. Minimnya pengetahuan masyarakat terhadap aplikasi Laporkitong menyebabkan banyak permasalahan. Maka dari itu perlu dilakukan analisis mengenai adopsi pada aplikasi Laporkitong. Penelitian ini bertujuan untuk menyelidiki pengaruh faktor Kualitas yang Dirasakan, Kendali yang Dirasakan, dan Kemudahan Penggunaan yang Dirasakan sebagai penentu keinginan penduduk untuk menggunakan aplikasi Laporkitong, dengan menggunakan Model Penerimaan Teknologi (TAM) dan teori Kesuksesan Sistem Informasi (IS D&M) DeLone dan McLean. Sebanyak 160 responden valid dikumpulkan berdasarkan teknik purposive sampling dan dievaluasi menggunakan Partial Least Square Structural Equation Modeling (PLS-SEM). Hasilnya menunjukkan bahwa semua tujuh hipotesis diterima dengan R-square niat untuk menggunakan adalah 0,273, menunjukkan bahwa 27,3% variasi model dapat menentukan hasilnya. Diskusi lebih lanjut dan kesimpulan mengenai implikasi kontribusi teoritis dan praktis juga dibahas.   Kata kunci: laporkitong; pengendalian yang dirasakan; kemudahan penggunaan yang dirasakan; kualitas yang dirasakan; model penerimaan teknologi  

The Effect of Algorithmic Performance Appraisal on Employee Trust in Digital and Technology-Based Companies

Rini Anisyahrini, Winne Wardiani, Azizun Kurnia Ilahi, Anita Asnawi, Mochammad Arfani
Abstract: This study examines how employees perceive and trust Algorithmic Performance Appraisal (APA) in digital-native and technology-driven companies. Adopting Organizational Justice Theory, the Trust in Technology Framework, and… nd Cognitive Appraisal Theory, the research explores both the direct and indirect effects of APA on employee trust, with Perceived Procedural Fairness (PPF) as a mediating variable. The study uses a quantitative, cross-sectional approach, collecting data from 200 employees in technology-based organizations and analyzing the data with Partial Least Squares Structural Equation Modeling (PLS-SEM). Results show that APA significantly enhances both procedural fairness and employee trust, with PPF playing a partial mediating role in this relationship. These findings underscore the importance of transparency, procedural legitimacy, and avenues for employee voice in cultivating trust in algorithmic systems. The study’s theoretical contribution lies in its integration of multiple perspectives on trust and fairness within algorithmic HR management. The practical implication calls for the careful design and implementation of APA systems that employees perceive as fair and trustworthy. Future research should investigate these relationships in longitudinal and multi-contextual settings to deepen the understanding of trust dynamics in evolving AI-mediated work environments.