Indonesian Journal of Information Systems

Forensic Investigation of SEO Manipulation in Moodle LMS: Uncovering Illegal Content in Educational Platforms

Tri Rochmadi — 2025-08-23

Learning Management Systems (LMS) like Moodle are frequently targeted by covert cyberattacks that exploit the credibility of academic domains for illicit purposes. This study uncovers an SEO-based attack method that infiltrates hidden links to gambling sites through Moodle's public directory. Digital forensic methodology was used to trace the perpetrators' footprints from server logs, HTML/JS files, and activity in Google Search Console. The results revealed a comprehensive exploit: fake admin accounts, redirect file injection, and Google indexing manipulation. This research not only highlights an under-researched threat but also offers a mitigation framework based on the ISO/IEC 27001 standard. Key contributions include identifying SEO-based attack techniques in LMSs, analyzing digital artifacts for perpetrator attribution, and strengthening cybersecurity governance in educational institutions.

Coral Detection based on Optimised Lightweight YOLO Model

Raymond Erz Saragih — 2025-08-23

Coral reefs are essential marine ecosystems that face significant threats due to climate change, pollution, and overfishing. Effective monitoring is crucial for conservation efforts, but traditional methods are labor-intensive and inefficient. This study proposes a deep learning-based coral detection model built based on the YOLOv8 architecture, specifically for nano and small. In addition, the Ghost modules and Ghost bottlenecks were utilized to modify the original YOLOv8 small. The proposed model was trained on an underwater coral dataset and evaluated in terms of precision, recall, and mean Average Precision (mAP) metrics. Experimental results demonstrate that the YOLOv8 small model and YOLOv8 small model with Ghost modules achieved a mAP of 53.675% and 55.88%, respectively, while maintaining a compact model size. This work contributes to developing efficient and lightweight coral detection systems to support conservation efforts.

Development of Foot Mat Sensor Technology for Foot Identification and BMI-Based Biomechanical Risk Prediction

Evanita — 2025-08-23

This study advances the Foot Mat Sensor (FMS) technology to discern foot morphology and forecast biomechanical vulnerabilities predicated on Body Mass Index (BMI). The proposed system amalgamates the analysis of plantar pressure with various biomechanical parameters, including heel pressure, midfoot pressure, forefoot pressure, and foot contact area (FCA). Data were collected from ten participants exhibiting a spectrum of BMI, foot morphology (High Arch, Normal Arch, and Low Arch), foot length, contact area, and asymmetrical plantar pressure. The findings indicated a statistically significant correlation between elevated BMI (>25), irregular plantar pressure distribution, and heightened biomechanical risk. Participants with high BMI and Low Arch (LA) foot morphology demonstrated an augmented risk, with plantar pressure asymmetry ≥20 kPa as the principal indicator. The prediction model founded on the Random Forest algorithm attained an accuracy of 85% in categorizing biomechanical risk into low, medium, and high classifications. The Digital Footprint Scanner technology, innovated through this research, is anticipated to augment the efficacy of personalized and precise diagnostics and the prophylaxis of biomechanical injuries. This endeavor contributes to formulating a data-driven system for the early detection of biomechanical risks, with applications in medicine, athletics, and rehabilitation.

Optimizing Sentiment Analysis of Hotel Reviews Using PCA and Machine Learning for Tourism Business Decision Support

PUTRI TAQWA PRASETYANINGRUM — 2025-08-23

Sentiment analysis of hotel reviews provides valuable insights for improving customer satisfaction and service quality in the tourism industry. However, the high dimensionality and unstructured nature of review data pose challenges in extracting meaningful insights. This study optimizes sentiment analysis by applying Principal Component Analysis (PCA) for dimensionality reduction and utilizing machine learning models for classification. The proposed approach involves data preprocessing, feature selection using PCA, model training, and performance evaluation. Experimental results show that PCA enhances classification accuracy and computational efficiency by eliminating redundant features, improving sentiment prediction. The comparative analysis demonstrates that the Voting classifier achieves the highest accuracy (95.29%) and F-score (97.50%), while the BiLSTM-FNN model attains the highest recall (99.95%). These findings highlight the potential of PCA-based sentiment analysis in supporting data-driven decision-making for hotel management, enabling enhanced service quality, improved customer experience, and effective marketing strategies.

Investigating the challenges, benefits, and applications of digital health in South Africa: A PRISMA process

Tshenolo Eunice Kgashwane — 2025-08-23

Digital health technologies have the ability to enhance the quality of healthcare. The usage of digital technologies (digital gadgets and their related apps, platforms, and websites) has led to numerous claims in public health and medical research about an impending breakthrough in the health sector, preventative medicine, and public health. Nevertheless, it is crucial to take a more cynical stance when evaluating the effects and consequences of digital health. Moreover, digital health adoption in developing and developed countries has disclosed several advantages, challenges, and applications. Thus, this study aimed to investigate the challenges, benefits, and applications of digital health in South Africa. The methodology utilized in this study was a qualitative systematic review through the PRISMA process and made use of documents such as accredited academic journals, articles, and books to gather data. This study used a sequential sampling method, and data were collected until saturation was reached. For purposes of data analysis, the study used thematic analysis to discover themes from the gathered data. The findings of this study revealed barriers that impede digital health adoption in South Africa. These barriers include technical, supportive policies, skilled manpower, and many more. Furthermore, work is needed to explore how the adoption of digital health technologies will affect the work of individuals. It is recommended that end users be trained on how to use digital health systems and many other things.

Recognition of the Lima Pandawa Shadow Puppet characters utilizing Principal Component Analysis (PCA) for feature extraction and K-Nearest Neighbor (KNN) for classification

Ida WIdaningrum — 2025-08-23

The traditional type of puppet-shadow play, Wayang Kulit, is an integral component of Indonesian culture. The Pandawa Lima, protagonists in this artistic medium, have great importance not just in narrative but also in embodying moral and ethical principles. The automated identification of these characters can optimize a range of applications, such as instructional resources, digital preservation, and interactive displays. This research intends to maximize the advantages of PCA and KNN by utilizing their respective strengths: PCA's capacity to decrease data dimensionality and KNN's efficacy in classification tasks. An expected outcome of this combination is an enhancement in recognition accuracy without compromising computational efficiency. The classification matrix indicates that the model achieved a 78% accuracy rate. Class-specific accuracy, recall, and F1-scores are as follows: arjuna achieves a precision of 0.85, recall of 0.91, and F1 Score of 0.87. Macro averages for precision, recall, and F1 are 0.77, 0.76, and 0.74, respectively. Weighted averages for these metrics are 0.80, 0.78, and 0.77, respectively. The model exhibits strong performances on Arjuna, Sadewa, and Yudistira, but encounters difficulties with Bima and Nakula.

Forced eLearning Acceptance using TPB: High School vs University Students

Samiaji Sarosa — 2025-08-23

Covid 19 Pandemic has forced Indonesian students to utilize eLearning tools. This article tests the acceptance of forced eLearning by Indonesian high school and students using Theory of Planned Behavior. The study extended original TPB to include Perceived Cost, Perceived Risks, Trust (both organization and application), Perceived Ease of Used, Perceived Usefulness, Controllability, and Self-efficacy. We also conducted Multi Group Analysis to see if university students and high school students have differences in their acceptance.

Instagram Through Her Eyes: Exploring Female Instagram Content Creators’ Motivations for Content Creation

Senamile Mlangeni — 2025-08-23

Instagram has emerged as a dominant social media platform globally, particularly among young female users who engage actively with visual content and digital narratives. While existing studies have explored the psychological implications of social media usage, few have specifically focused on the motivations behind content creation and the nature of posts, especially within the context of South African universities. This study investigates these motivations among female students aged 18–35 at a University of Technology. A mixed-methods approach was employed, incorporating structured surveys, semi-structured interviews, and content analysis of Instagram posts over a three-month period. The findings indicate that motivations such as self-expression and validation underpin much of the content shared. The study contributes to the understanding of online identity construction and emotional regulation in digital spaces, offering insights into mental health awareness, digital literacy education, and inclusive platform design. By examining female students' Instagram engagement in the Global South, this research fills a contextual and theoretical gap, shedding light on the intersection of social media with unique cultural, academic, and technological dynamics.

Design of Web-Based Motor Vehicle Spare Parts Sales Application Using the Rapid Application Development (RAD) Method

Alexander Wirapraja — 2025-08-23

The development of technology, especially in the industrial era 4.0 and the era of technological disruption accompanied by the increasing literacy of society in technology, has influenced the operations of a business company, especially in their marketing methods as the front line of a business process. Company X in Surabaya, which is engaged in the sale of motor vehicle spare parts, is one of the companies that is aware that the market continues to grow and they must follow these changes by designing a sales website to increase their revenue. This sales website was developed using the rapid application development (RAD) method because this method is suitable for developing software on a small to medium scale and has advantages in terms of efficiency of work time. The results obtained from the design of this sales information system software are a system that can help company X in managing spare part sales as a whole with features that include product catalogs, product transactions, multiple payments, shipping calculations, return menus, customer satisfaction ratings and sales reports per time period.