arXiv subjects

Mike Wa Nkongolo

Publications and source records attributed to Mike Wa Nkongolo.

8 recordsLinked to original sources

arXiv2026

Pluralism in AI Governance: Toward Sociotechnical Alignment and Normative Coherence

This paper examines the challenge of embedding public values into national artificial intelligence (AI) governance frameworks, a task complicated by the sociotechnical nature of contemporary systems. As AI permeates domains such as healthcare, justice, and public administration, legitimacy depends not only on technical correctness but on alignment with societal norms, democratic principles, and human dignity. Traditional paradigms focused on model safety or market efficiency neglect broader institutional contexts. To address this, the study synthesises frameworks including Full-Stack Alignment, Thick Models of Value, Value Sensitive Design, and Public Constitutional AI, alongside comparative analysis of jurisdictions such as the EU, US, China, UK, Brazil, and South Africa (SA). It introduces a layered framework linking values, mechanisms, and strategies, and maps tensions such as fairness versus efficiency, transparency versus security, and privacy versus equity. Findings reveal a pluralism of regulatory philosophies, with SA sovereignty-oriented approach offering a distinctive counterpoint. The study contributes a holistic, value-sensitive model of AI governance, reframing regulation as a proactive mechanism for embedding public values into sociotechnical systems.

cs.CY↗

arXiv2025

Integrating Public Input and Technical Expertise for Effective Cybersecurity Policy Formulation

The evolving of digital transformation and increased use of technology comes with increased cyber vulnerabilities, which compromise national security. Cyber-threats become more sophisticated as the technology advances. This emphasises the need for strong risk mitigation strategies. To define strong and robust cybersecurity, policies requires an integrated approach of balancing technical expertise with public input. This paper aims to explore strategies used to balance technical expertise and public input to develop effective and robust cybersecurity policies. It also studied how the effective integration of technical expertise with public input is critical to developing effective strategies and resilient cybersecurity frameworks that strengthens national security. A lack of a holistic approach and collaborative efforts to cybersecurity can hinder the effectiveness of cybersecurity policies. This paper followed a systematic literature review with bibliometric analysis using the PRISMA methodology to explore how technical expertise and public input can be integrated to guide cybersecurity policy making. The thematic analysis identified five important themes in developing effective cybersecurity policies, these key themes are: Multi-Stakeholder Involvement and Human Centric Approaches (MSI & HCA), Governance and Policy Frameworks (GPF), Technical Infrastructure (TI), Evaluation and Compliance (EC), and Legal Rights and Sovereignty (LRS). The synthesis shows that there is no adequate exploration of collaborative efforts which undermines the effectiveness of the cybersecurity policies. The findings suggest that inclusive, flexible governance strategies that integrate public input at every stage are necessary for future cybersecurity policy research and practice, which must shift away from a primarily technical and legal perspective.

cs.CR↗

arXiv2025

Improving News Recommendations through Hybrid Sentiment Modelling and Reinforcement Learning

News recommendation systems rely on automated sentiment analysis to personalise content and enhance user engagement. Conventional approaches often struggle with ambiguity, lexicon inconsistencies, and limited contextual understanding, particularly in multi-source news environments. Existing models typically treat sentiment as a secondary feature, reducing their ability to adapt to users' affective preferences. To address these limitations, this study develops an adaptive, sentiment-aware news recommendation framework by integrating hybrid sentiment analysis with reinforcement learning. Using the BBC News dataset, a hybrid sentiment model combines VADER, AFINN, TextBlob, and SentiWordNet scores to generate robust article-level sentiment estimates. Articles are categorised as positive, negative, or neutral, and these sentiment states are embedded within a Q-learning architecture to guide the agent in learning optimal recommendation policies. The proposed system effectively identifies and recommends articles with aligned emotional profiles while continuously improving personalisation through iterative Q-learning updates. The results demonstrate that coupling hybrid sentiment modelling with reinforcement learning provides a feasible, interpretable, and adaptive approach for user-centred news recommendation.

cs.IR↗

arXiv2025

A Proactive Insider Threat Management Framework Using Explainable Machine Learning

Over the years, the technological landscape has evolved, reshaping the security posture of organisations and increasing their exposure to cybersecurity threats, many originating from within. Insider threats remain a major challenge, particularly in sectors where cybersecurity infrastructure, expertise, and regulations are still developing. This study proposes the Insider Threat Explainable Machine Learning (IT-XML) framework, which integrates the Cross-Industry Standard Process for Data Mining (CRISP-DM) with Hidden Markov Models (HMM) to enhance proactive insider threat management and decision-making. A quantitative approach is adopted using an online questionnaire to assess employees' knowledge of insider threat patterns, access control, privacy practices, and existing policies across three large data-sensitive organisations. The IT-XML framework provides assessment capabilities through survey-based data, HMM-driven pattern recognition for security maturity classification, and evidence-based recommendations for proactive threat mitigation. The framework classified all organisations at the developing security maturity level with 97-98% confidence and achieved a classification accuracy of 91.7%, identifying audit log access limits as the most critical control. Random Forest analysis highlighted vendor breach notifications (0.081) and regular audit log reviews (0.052) as key determinants of resilience. Explainability methods such as SHAP and LIME improved model transparency and interpretability, demonstrating the framework's potential to strengthen insider threat management practices.

cs.CR↗

arXiv2024

A Multilingual Sentiment Lexicon for Low-Resource Language Translation using Large Languages Models and Explainable AI

South Africa and the Democratic Republic of Congo (DRC) present a complex linguistic landscape with languages such as Zulu, Sepedi, Afrikaans, French, English, and Tshiluba (Ciluba), which creates unique challenges for AI-driven translation and sentiment analysis systems due to a lack of accurately labeled data. This study seeks to address these challenges by developing a multilingual lexicon designed for French and Tshiluba, now expanded to include translations in English, Afrikaans, Sepedi, and Zulu. The lexicon enhances cultural relevance in sentiment classification by integrating language-specific sentiment scores. A comprehensive testing corpus is created to support translation and sentiment analysis tasks, with machine learning models such as Random Forest, Support Vector Machine (SVM), Decision Trees, and Gaussian Naive Bayes (GNB) trained to predict sentiment across low resource languages (LRLs). Among them, the Random Forest model performed particularly well, capturing sentiment polarity and handling language-specific nuances effectively. Furthermore, Bidirectional Encoder Representations from Transformers (BERT), a Large Language Model (LLM), is applied to predict context-based sentiment with high accuracy, achieving 99% accuracy and 98% precision, outperforming other models. The BERT predictions were clarified using Explainable AI (XAI), improving transparency and fostering confidence in sentiment classification. Overall, findings demonstrate that the proposed lexicon and machine learning models significantly enhance translation and sentiment analysis for LRLs in South Africa and the DRC, laying a foundation for future AI models that support underrepresented languages, with applications across education, governance, and business in multilingual contexts.

cs.CL↗

arXiv2024

Blockchain security for ransomware detection

Blockchain networks are critical for safeguarding digital transactions and assets, but they are increasingly targeted by ransomware attacks exploiting zero-day vulnerabilities. Traditional detection techniques struggle due to the complexity of these exploits and the lack of comprehensive datasets. The UGRansome dataset addresses this gap by offering detailed features for analysing ransomware and zero-day attacks, including timestamps, attack types, protocols, network flows, and financial impacts in bitcoins (BTC). This study uses the Lazy Predict library to automate machine learning (ML) on the UGRansome dataset. The study aims to enhance blockchain security through ransomware detection based on zero-day exploit recognition using the UGRansome dataset. Lazy Predict streamlines different ML model comparisons and identifies effective algorithms for threat detection. Key features such as timestamps, protocols, and financial data are used to predict anomalies as zero-day threats and to classify known signatures as ransomware. Results demonstrate that ML can significantly improve cybersecurity in blockchain environments. The DecisionTreeClassifier and ExtraTreeClassifier, with their high performance and low training times, are ideal candidates for deployment in real-time threat detection systems.

cs.CR↗

arXiv2024

Using ARIMA to Predict the Expansion of Subscriber Data Consumption

This study discusses how insights retrieved from subscriber data can impact decision-making in telecommunications, focusing on predictive modeling using machine learning techniques such as the ARIMA model. The study explores time series forecasting to predict subscriber usage trends, evaluating the ARIMA model's performance using various metrics. It also compares ARIMA with Convolutional Neural Network (CNN) models, highlighting ARIMA's superiority in accuracy and execution speed. The study suggests future directions for research, including exploring additional forecasting models and considering other factors affecting subscriber data usage.

cs.LG↗

arXiv2024

Ransomware Detection and Classification Using Random Forest: A Case Study with the UGRansome2024 Dataset

Cybersecurity faces challenges in identifying and mitigating ransomware, which is important for protecting critical infrastructures. The absence of datasets for distinguishing normal versus abnormal network behaviour hinders the development of proactive detection strategies against ransomware. An obstacle in proactive prevention methods is the absence of comprehensive datasets for contrasting normal versus abnormal network behaviours. The dataset enabling such contrasts would significantly expedite threat anomaly mitigation. In this study, we introduce UGRansome2024, an optimised dataset for ransomware detection in network traffic. This dataset is derived from the UGRansome data using an intuitionistic feature engineering approach that considers only relevant patterns in network behaviour analysis. The study presents an analysis of ransomware detection using the UGRansome2024 dataset and the Random Forest algorithm. Through encoding and feature relevance determination, the Random Forest achieved a classification accuracy of 96% and effectively identified unusual ransomware transactions. Findings indicate that certain ransomware variants, such as those utilising Encrypt Decrypt Algorithms (EDA) and Globe ransomware, have the highest financial impact. These insights have significant implications for real-world cybersecurity practices, highlighting the importance of machine learning in ransomware detection and mitigation. Further research is recommended to expand datasets, explore alternative detection methods, and address limitations in current approaches.

cs.CR↗