Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Journal Innovation in Information and Computer Technology
Mahmud
Institut Teknologi dan Bisnis Bina Sriwijaya Palembang

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Transformer-Based Fake News Detection Model for Semantic Analysis of Social Media Content Mahmud; Muhammad Ridho Ardiansyah
Journal Innovation in Information and Computer Technology Vol. 3 No. 1 (2026): (January) Journal Innovation in Information and Computer Technology (JICTECH)
Publisher : PT. Altaf Publishing Corp

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70895/jictech.v3i1.113

Abstract

The rapid growth of social media platforms has significantly increased the spread of misinformation and fake news, which can negatively influence public opinion and social stability. Detecting fake news automatically has therefore become an important research topic in the fields of natural language processing and machine learning. This study proposes a transformer-based fake news detection model using Bidirectional Encoder Representations from Transformers (BERT) to perform semantic analysis on social media news content. The proposed framework consists of several stages including dataset preparation, text preprocessing, contextual feature extraction using BERT embeddings, model training, and performance evaluation. The experiments were conducted using the FakeNewsNet dataset, which contains verified fake and real news articles collected from online sources. The dataset was divided into training and testing subsets, and the model was fine-tuned using a BERT-based classification architecture. The performance of the proposed model was evaluated using standard classification metrics including accuracy, precision, recall, and F1-score. Experimental results show that the proposed model achieved an accuracy of 94.3%, with precision, recall, and F1-score values of 93.7%, 92.9%, and 93.3%, respectively. These results demonstrate that transformer-based language models are highly effective in capturing contextual semantic relationships within textual data. The findings suggest that integrating transformer architectures into misinformation detection systems can significantly improve the accuracy and robustness of fake news detection in social media environments.
Deep Learning Approach for Anomaly Detection in Digital Financial Transactions Mahmud; Akhmad Sayuti
Journal Innovation in Information and Computer Technology Vol. 2 No. 1 (2025): (January) Journal Innovation in Information and Computer Technology (JICTECH)
Publisher : PT. Altaf Publishing Corp

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70895/jictech.v2i1.122

Abstract

The rapid growth of digital financial services has significantly increased the volume and complexity of financial transactions, creating new challenges in maintaining transaction security and preventing fraudulent activities. Anomaly detection has become an essential mechanism for identifying suspicious transaction patterns that may indicate potential fraud within digital financial systems. This study aims to develop a deep learning–based approach for detecting anomalies in digital financial transactions by analyzing behavioral patterns within transaction datasets. The proposed method utilizes a deep neural network architecture to analyze multiple transaction attributes such as transaction amount, transaction time, user identification, merchant category, and device information. Prior to model development, transaction data undergoes several preprocessing stages including data cleaning, data transformation, and feature normalization to ensure data quality and compatibility with deep learning algorithms. The dataset is divided into training and testing subsets to evaluate the effectiveness of the proposed model in identifying anomalous transactions. Experimental results demonstrate that the deep learning model achieves strong performance in anomaly detection tasks. The proposed model obtained an accuracy of 96.8%, precision of 94.5%, recall of 92.7%, and an F1-score of 93.6%. In addition, the ROC-AUC value of 0.97 indicates that the model is highly effective in distinguishing between normal and anomalous transactions. These results show that deep learning techniques are capable of capturing complex transaction patterns and improving the reliability of fraud detection systems in digital financial environments. The findings of this study suggest that the integration of deep learning–based anomaly detection models into financial monitoring systems can significantly enhance transaction security and assist financial institutions in detecting suspicious activities more efficiently. As digital financial ecosystems continue to evolve, intelligent anomaly detection systems will play an important role in strengthening financial security and supporting the development of secure digital financial services.
Co-Authors Akhmad Sayuti