Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hlaudi Daniel Masethe has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Neuromorphic-Inspired Language Identification for Low-Resource Code-Switched Texts Using Spiking Neural Networks

    by Hlaudi D. Masethe, Mosima A. Masethe

    Multilingual code-switched language identification remains a challenging task due to frequent language alternation, lexical ambiguity, and the limited availability of annotated corpora for low-resource languages. While transformer-based language models have demonstrated strong performance, their computational complexity motivates the exploration of more efficient neuromorphic approaches. This study proposes an optimized Spiking Neural Network (SNN) framework for multilingual code-switched language identification using spike-based neural computation. Text data are preprocessed and represented using Term Frequency–Inverse Document Frequency (TF-IDF) feature vectors, which are transformed into temporal spike trains through a rate-coding mechanism over a fixed simulation window. The encoded spike sequences are processed by a feedforward SNN employing Leaky Integrate-and-Fire (LIF) neurons. Hyperparameters are optimized using Optuna to improve classification performance. The proposed model is evaluated on a balanced multilingual code-switched dataset and compared with classical machine learning models, including Logistic Regression, Support Vector Machine, and Random Forest, as well as deep learning and transformer-based models, including BiLSTM, mBERT, AfroXLMR, and XLM-RoBERTa. Experimental results demonstrate that the optimized SNN achieves an overall classification accuracy of 81%, outperforming the baseline SNN while remaining competitive with several state-of-the-art neural models. Statistical validation using the Friedman and Nemenyi tests confirms significant performance differences among the evaluated classifiers while demonstrating that the optimized SNN performs competitively against several strong baselines. Although transformer models achieve the highest overall accuracy, the proposed SNN offers a computationally efficient neuromorphic alternative that combines temporal spike processing with stable learning behaviour for multilingual code-switched language identification. These findings demonstrate the potential of spike-based neural computing for low-resource multilingual natural language processing and provide a reproducible foundation for future neuromorphic language identification research.

  • Open Access

    An Explainable XGBoost-Based Model for Credit Card Fraud Detection in Highly Imbalanced Transaction Data

    by Hlaudi D. Masethe, Mosima A. Masethe, Z Mapundu, Pius A Owolawi, M Moeti

    Credit card fraud detection remains a challenging classification problem due to the severe imbalance between legitimate and fraudulent transactions, where conventional accuracy can provide a misleading assessment of model effectiveness. This study proposes an explainable machine learning model for credit card fraud detection by comparatively evaluating Logistic Regression, Random Forest, XGBoost, LightGBM, and CatBoost against a Dummy Classifier baseline. Model performance was assessed using balanced accuracy, precision, recall, F1-score, ROC-AUC, PR-AUC, confusion matrices, prediction errors, and computational training time. McNemar’s test was further employed to statistically assess differences in paired model predictions, while SHapley Additive exPlanations (SHAP) provided global and local interpretability of the best-performing model. Experimental results identified XGBoost as the strongest overall classifier, achieving a PR-AUC of 0.8231, ROC-AUC of 0.9752, fraud precision of 0.9259, recall of 0.7895, and F1-score of 0.8523. XGBoost additionally produced the fewest prediction errors and the shortest training time among the evaluated gradient-boosting models. McNemar’s test indicated a statistically significant difference in paired model predictions (p = 1.29 × 10⁻¹¹). SHAP analysis identified V14, V4, V12, V10, and V11 as the most influential features, while transaction-level explanations revealed how individual feature values contributed toward or against fraud predictions. The findings demonstrate that combining gradient boosting, imbalance-sensitive evaluation, statistical validation, and explainable AI can provide an accurate, computationally efficient, and interpretable approach to credit card fraud detection.

  • Open Access

    Robust breast cancer classification via ensemble learning: Integrating feature analysis and error evaluation techniques

    by Mosima A. Masethe, Hlaudi D. Masethe

    Breast cancer remains one of the leading causes of cancer-related mortality worldwide, highlighting the need for accurate and reliable computer-aided diagnostic methods. This study evaluates the effectiveness of ensemble learning techniques for classifying breast tumors as benign or malignant using clinical tumor features. A data-driven model was developed using a publicly available Kaggle breast cancer dataset. Four ensemble learning models, Random Forest, Gradient Boosting, AdaBoost, and Extra Trees, were trained and comparatively evaluated using accuracy, precision, recall, F1-score, and Receiver Operating Characteristic Area Under the Curve (ROC-AUC). Feature importance and error analyses were also conducted to identify influential predictors and assess model reliability. All evaluated models achieved excellent predictive performance, with classification accuracies above 96% and ROC-AUC values exceeding 0.99. The Extra Trees classifier demonstrated the best overall performance, achieving the highest accuracy, the lowest error rate, and superior sensitivity in detecting malignant tumors. Tumor characteristics related to perimeter, radius, and concave points were identified as the most influential features. Ensemble learning provides a robust and reliable approach for breast cancer classification, enabling highly accurate diagnostic predictions. The proposed model can support clinicians in early breast cancer detection and decision-making, potentially improving diagnostic accuracy and patient outcomes while reducing misclassification of malignant cases.

  • Bibliometric Analysis on Money Laundering Fraud Detection Using Generative Artificial Intelligence Models

    by Eminence Shabangu, Mosima A. Masethe, Hlaudi D. Masethe, Alex D. Dandadzi

    Money laundering remains a major challenge for financial institutions, particularly as traditional rule-based systems struggle to detect evolving fraud patterns. Recent advances in generative artificial intelligence (AI) offer promising directions, yet the extent and focus areas of existing research remain unclear. This study conducts a descriptive bibliometric analysis to map the research landscape connecting generative AI and anti-money laundering (AML) detection. A total of 748 peer-reviewed publications from Scopus and 54 from Web of Science were analyzed to identify key themes, leading contributors, co-authorship structures, keyword cooccurrence patterns, and citation trends. Using VOSviewer, the study visualizes research clusters and highlights emerging areas such as deep learning, synthetic data generation, and graphbased fraud detection. The analysis reveals growing scholarly attention to AI-driven AML methods but limited coverage of real-time and institution-specific applications. The findings clarify current research directions, expose gaps in the literature, and define opportunities where generative AI can further support AML innovation.


  • A Bibliometric Analysis of Quantum-Enhanced Neural Network Applications in Rare Disease Diagnosis

    by Fikile E Mokoka, Mosima A Masethe, Hlaudi D. Masethe, Alex Dandadzi

    Rare diseases encompass over 7,000 conditions and affect an estimated 350–400 million individuals worldwide. Despite their prevalence, research remains limited. This study presents a bibliometric analysis of Quantum-Enhanced Neural Network (QENN)-based models for rare disease prediction. A dataset of 516 peer-reviewed articles retrieved from the Scopus database was analysed to map publication trends, citation networks, co-authorship linkages, keyword co-occurrence, and country-level contributions from inception to 2025. Results indicate a marked increase in publications over the past five years, driven by advances in quantum computing, bioinformatics, and artificial intelligence. Key research clusters were identified in quantum machine learning, biomedical prediction, and rare disease diagnostics. The findings provide a quantitative overview of the intellectual structure of this emerging interdisciplinary domain and highlight future directions for developing robust quantum-enhanced models in healthcare analytics.

  • Open Access

    Optimising Contextual Embeddings for Meaning Conflation Deficiency Resolution in Low-Resourced Languages

    by Mosima A. Masethe, Sunday O. Ojo, Hlaudi D. Masethe

    Meaning conflation deficiency (MCD) presents a continual obstacle in natural language processing (NLP), especially for low-resourced and morphologically complex languages, where polysemy and contextual ambiguity diminish model precision in word sense disambiguation (WSD) tasks. This paper examines the optimisation of contextual embedding models, namely XLNet, ELMo, BART, and their improved variations, to tackle MCD in linguistic settings. Utilising Sesotho sa Leboa as a case study, researchers devised an enhanced XLNet architecture with specific hyperparameter optimisation, dynamic padding, early termination, and class-balanced training. Comparative assessments reveal that the optimised XLNet attains an accuracy of 91% and exhibits balanced precision–recall metrics of 92% and 91%, respectively, surpassing both its baseline counterpart and competing models. Optimised ELMo attained the greatest overall metrics (accuracy: 92%, F1-score: 96%), whilst optimised BART demonstrated significant accuracy improvements (96%) despite a reduced recall. The results demonstrate that fine-tuning contextual embeddings using MCD-specific methodologies significantly improves semantic disambiguation for under-represented languages. This study offers a scalable and flexible optimisation approach suitable for additional low-resource language contexts.


  • Open Access

    A Context-Aware Embedding Approach to Meaning Conflation Deficiency in Sesotho sa Leboa: Addressing Semantic Ambiguity

    by Mosima A. Masethe, Sunday O. Ojo, Hlaudi D. Masethe

    A major problem in Natural Language Processing (NLP) is Meaning Conflation Deficiency (MCD), especially in low-resource, morphologically rich languages like Sesotho sa Leboa. In downstream tasks like Word Sense Disambiguation (WSD), traditional word embeddings frequently perform poorly because they are unable to distinguish between a word's numerous senses. To ascertain how well various context-aware and multi-prototype word embedding models—such as ELMo, GPT-2, BERT, Universal Sentence Encoder, and hybrid versions of Doc2Vec and SBERT—resolve MCD, this study examines and assesses them. Standard classification measures (precision, recall, F1-score, and accuracy) as well as clustering-based metrics and visualisation approaches were used to assess the models after they were trained and tested on a sense-annotated Sesotho sa Leboa corpus. According to the results, deep contextual models—in particular, ELMo and GPT-2—perform noticeably better in terms of accuracy and sense separation than static and unsupervised models. With well-separated confusion matrices, ELMo showed excellent interpretability and the highest F1-score (93%) of any model. According to the results, context-aware architecture provides reliable MCD solutions as well as a scalable framework for improving WSD in language applications with limited resources. For future studies on semantic disambiguation in under-represented languages, the work offers fresh standards and perspectives.

  • Open Access

    Hybrid Transformer-Based Large Language Models for Word Sense Disambiguation in the Low-Resource Sesotho sa Leboa Language

    by Hlaudi Daniel Masethe, Mosima Anna Masethe, Sunday O. Ojo, Pius A. Owolawi, Fausto Giunchiglia

    This study addresses a lexical ambiguity issue in Sesotho sa Leboa that arises from terms with various meanings, often known as homonyms or polysemous words. When compared to, for instance, European languages, this lexical ambiguity in Sesotho sa Leboa causes computational semantic problems in NLP when trying to identify the lexicon of a language. In other words, it is challenging to determine the proper lexical category and sense of words due to this ambiguity problem. In order to address the issue of polysemy in the Sesotho sa Leboa language, this study set out to create a word sense discrimination (WSD) scheme using a corpus-based hybrid transformer-based architecture and deep learning models. Additionally, the performance of baseline and improved machine learning models for a sequence-based natural language processing (NLP) task was assessed and compared. The baseline models included RNN-LSTM, BiGRU, LSTMLM, DeBERTa, and DistilBERT, with accuracies of 61%, 79%, 74%, 70%, and 64%, respectively. Among these, BiGRU emerged as the strongest performer, leveraging its bidirectional architecture to achieve the highest baseline accuracy. Transformer-based models, such as DeBERTa and DistilBERT, demonstrated moderate performance, with the latter prioritizing efficiency at the cost of accuracy. The enhanced results explored optimization techniques and hybrid model architectures to improve performance. BiGRU, optimized with ADAM, achieved an accuracy of 84%, while BiGRU with attention mechanisms further improved to 85%, showcasing the effectiveness of these enhancements. Hybrid models integrating BiGRU with transformer architectures demonstrated varying results. BiGRU + DeBERTa and BiGRU + ALBERT achieved the highest accuracies of 85% and 84%, respectively, highlighting the complementary strengths of bidirectional context modeling and advanced transformer-based contextual understanding. Conversely, the Hybrid BiGRU + RoBERTa model underperformed, with an accuracy of 70%, indicating potential mismatches in model synergy. These findings highlight how crucial hybridization and optimization are to reaching cutting-edge performance on NLP tasks. According to this study’s findings, the most promising approaches for fusing accuracy and efficiency are attention-based BiGRU and BiGRU–transformer hybrids, especially those that incorporate DeBERTa and ALBERT. To further improve speed, future research should concentrate on exploring task-specific optimizations and improving hybrid model integration.


  • Open Access

    Context-Aware Embedding Techniques for Addressing Meaning Conflation Deficiency in Morphologically Rich Languages Word Embedding: A Systematic Review and Meta Analysis

    by Mosima Anna Masethe, Hlaudi Daniel Masethe, Sunday O. Ojo

    This systematic literature review aims to evaluate and synthesize the effectiveness of various embedding techniques—word embeddings, contextual word embeddings, and context-aware embeddings—in addressing Meaning Conflation Deficiency (MCD). Using the PRISMA framework, this study assesses the current state of research and provides insights into the impact of these techniques on resolving meaning conflation issues. After a thorough literature search, 403 articles on the subject were found. A thorough screening and selection process resulted in the inclusion of 25 studies in the meta-analysis. The evaluation adhered to the PRISMA principles, guaranteeing a methodical and lucid process. To estimate effect sizes and evaluate heterogeneity and publication bias among the chosen papers, meta-analytic approaches were utilized such as the tau-squared (τ2) which represents a statistical parameter used in random-effects, H-squared (H2) is a statistic used to measure heterogeneity, and I-squared (I2) quantify the degree of heterogeneity. The meta-analysis demonstrated a high degree of variation in effect sizes among the studies, with a τ2 value of 8.8724. The significant degree of heterogeneity was further emphasized by the H2 score of 8.10 and the I2 value of 87.65%. A trim and fill analysis with a beta value of 5.95, a standard error of 4.767, a Z-value (or Z-score) of 1.25 which is a statistical term used to express the number of standard deviations a data point deviates from the established mean, and a p-value (probability value) of 0.2 was performed to account for publication bias which is one statistical tool that can be used to assess the importance of hypothesis test results. The results point to a sizable impact size, but the estimates are highly unclear, as evidenced by the huge standard error and non-significant p-value. The review concludes that although contextually aware embeddings have promise in treating Meaning Conflation Deficiency, there is a great deal of variability and uncertainty in the available data. The varied findings among studies are highlighted by the large τ2, I2, and H2 values, and the trim and fill analysis show that changes in publication bias do not alter the impact size’s non-significance. To generate more trustworthy insights, future research should concentrate on enhancing methodological consistency, investigating other embedding strategies, and extending analysis across various languages and contexts. Even though the results demonstrate a significant impact size in addressing MCD through sophisticated word embedding techniques, like context-aware embeddings, there is still a great deal of variability and uncertainty because of various factors, including the different languages studied, the sizes of the corpuses, and the embedding techniques used. These differences show how future research methods must be standardized to guarantee that study results can be compared to one another. The results emphasize how crucial it is to extend the linguistic scope to more morphologically rich and low-resource languages, where MCD is especially difficult. The creation of language-specific models for low-resource languages is one way to increase performance and consistency across Natural Language Processing (NLP) applications in a practical sense. By taking these actions, we can advance our understanding of MCD more thoroughly, which will ultimately improve the performance of NLP systems in a variety of language circumstances.


  • Open Access

    Word Sense Disambiguation for Morphologically Rich Low-Resourced Languages: A Systematic Literature Review and Meta-Analysis

    by Hlaudi Daniel Masethe, Mosima Anna Masethe, Sunday Olusegun Ojo, Fausto Giunchiglia, Pius Adewale Owolawi

    In natural language processing, word sense disambiguation (WSD) continues to be a major difficulty, especially for low-resource languages where linguistic variation and a lack of data make model training and evaluation more difficult. The goal of this comprehensive review and meta-analysis of the literature is to summarize the body of knowledge regarding WSD techniques for low-resource languages, emphasizing the advantages and disadvantages of different strategies. A thorough search of several databases for relevant literature produced articles assessing WSD methods in low-resource languages. Effect sizes and performance measures were extracted from a subset of trials through analysis. Heterogeneity was evaluated using pooled effect and estimates were computed by meta-analysis. The preferred reporting elements for systematic reviews and meta-analyses (PRISMA) were used to develop the process for choosing the relevant papers for extraction. The meta-analysis included 32 studies, encompassing a range of WSD methods and low-resourced languages. The overall pooled effect size indicated moderate effectiveness of WSD techniques. Heterogeneity among studies was high, with an I2 value of 82.29%, suggesting substantial variability in WSD performance across different studies. The (τ2) tau value of 5.819 further reflects the extent of between-study variance. This variability underscores the challenges in generalizing findings and highlights the influence of diverse factors such as language-specific characteristics, dataset quality, and methodological differences. The p-values from the meta-regression (0.454) and the meta-analysis (0.440) suggest that the variability in WSD performance is not statistically significantly associated with the investigated moderators, indicating that the performance differences may be influenced by factors not fully captured in the current analysis. The absence of significant p-values raises the possibility that the problems presented by low-resource situations are not yet well addressed by the models and techniques in use.