Libyan Journal of Informatics

Enhancing Vaccine Reaction Detection from Social Media Using Optimized Transformer Fine-Tuning

2025-11-18T21:02:55+00:00

This paper describes the system developed by the UoT team for Task 6 of the 10th Social Media Mining for Health (#SMM4H) Shared Tasks, which focused on detecting personally experienced vaccine reactions in social media posts. We fine-tuned the CardiffNLP Twitter-RoBERTa-Large model using optimized training settings and data preprocessing strategies. Our best submission achieved an F1-score of 0.945 on the test set, outperforming the average system and nearing the benchmark score of 0.946. We describe our training pipeline, evaluation metrics, and results, and compare our system with both large language models and benchmark transformer-based models.

A Taxonomy of Success and Failure Factors in Requirements Engineering for Sustainable Software

2025-11-07T23:41:13+00:00

Requirements Engineering (RE) is a crucial phase in the Software Development Life Cycle (SDLC) that significantly influences the success or failure of software projects. Despite its importance, there remains no unified taxonomy that systematically classifies the key factors influencing RE outcomes, particularly from a sustainability perspective. This study addresses this gap by conducting a systematic literature review that encompasses approximately twenty-five peer-reviewed studies published between 2010 and 2024. The identified findings were organized into six main categories: Requirements, People, Process, Communication, Tools & Technology, and Documentation, which represent the core dimensions of RE practice. Within each category, success and failure factors were synthesized to illustrate how they influence sustainable software outcomes. The resulting Ishikawa-based taxonomy provides a comprehensive diagnostic framework that integrates technical, human, and organizational aspects to support sustainability-oriented RE practices. The study contributes a structured foundation for assessing RE performance and guiding future sustainability modeling. Future work will focus on empirically validating the proposed taxonomy through case studies and surveys to evaluate its practical applicability in real-world software projects.

Gene Selection for Breast Cancer Classification Using T-Test Filtering and Wrapper-Based Optimization

2025-11-11T16:14:42+00:00

Accurate classification of breast cancer using gene expression data is challenged by the high dimensionality and noise inherent in microarray datasets. This study proposes and evaluates a hybrid feature selection pipeline that integrates T-Test filtering with four wrapper-based optimization methods: Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), Genetic Algorithms (GA), and Hill Climbing.

The T-Test was first used to reduce the initial feature space, after which each wrapper method was used to identify an optimal gene subset based on classifier performance. Experimental results show that SFS achieved the highest classification accuracy (98%) and AUC (0.99), while Hill Climbing offered the fastest execution time (1.68 seconds) but with a trade-off in specificity. Notably, the genes SFRP1 and CNTNAP3 were recurrently selected by different methods, suggesting their potential as key biomarkers. To further clarify these findings, we conducted an in-depth analysis of gene overlaps using Jaccard indices and explored the biological roles of selected genes, revealing SFRP1's tumor-suppressive function via Wnt pathway inhibition and CNTNAP3's emerging prognostic value in various cancers.

These findings emphasis the effectiveness of hybrid selection strategies and provide crucial insights into the trade-offs between classifier performance, computational cost, and gene stability in breast cancer classification. This extended analysis incorporates additional performance visualizations, detailed overlap metrics to offer a comprehensive view of hybrid feature selection's applicability in bioinformatics.

Enhancing Local Area Network Security Through Penetration Testing and Port Security

2025-11-03T17:06:49+00:00

Local Area Networks (LANs) remain highly vulnerable to protocol-based attacks that exploit weaknesses in essential network services. Among the most common attacks are Dynamic Host Configuration Protocol (DHCP) starvation, Address Resolution Protocol (ARP) spoofing, and Virtual Local Area Network (VLAN) hopping, which can severely compromise network confidentiality, integrity, and availability. This study investigates the effectiveness of penetration testing in identifying and mitigating such vulnerabilities within LAN environments. A simulated network was designed using GNS3, and controlled attacks were executed using Kali Linux and the Yersinia toolset to evaluate network resilience. Based on the penetration testing results, vulnerabilities were identified and mitigated using a single security mechanism, namely Port Security. The experimental results demonstrate that applying Port Security significantly reduced the number of successful attacks and improved overall network security. The findings highlight the importance of penetration testing as a practical approach for enhancing LAN security and provide cost-effective recommendations suitable for small and medium-sized organizations.

Digital Transformation in Libyan Banks

2026-01-06T04:45:23+00:00

This article examines digital transformation (DT) in the Libyan banking sector, a context characterized by prolonged political instability, regulatory centralization, and economic uncertainty. Using a qualitative comparative case study approach, four Libyan banks representing different levels of DT maturity were analyzed. Data were collected through twenty face-to-face interviews with bank executives and employees, complemented by internal reports and archival documents. The findings reveal that DT adoption is shaped by six interrelated factors: (1) leadership decision-making orientation, (2) ownership structure, (3) levels of bureaucracy and formalization, (4) human resource skills and training, (5) strategic clarity regarding technological development, and (6) investment capacity. Although all banks operate under the same national conditions, the relative influence of these factors varies significantly across cases, resulting in divergent DT trajectories. Rather than pursuing DT as an innovation-driven strategy, Libyan banks primarily adopt digital technologies to ensure operational continuity, regulatory compliance, and institutional survival. This study contributes to DT literature by highlighting transformation dynamics in fragile and conflict-affected environments.