Mosima  Anna Masethe

Ms. Mosima Anna Masethe

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 October 2024 in Computers
Verified
Journal Article
Open access
PDF file
MMMosima Anna Masethe
Mosima Anna Masethe
HMHlaudi Daniel Masethe
Hlaudi Daniel Masethe
Sunday Olusegun OjoSunday Olusegun Ojo
Sunday Olusegun 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.

4 September 2024 in Information
Verified
Journal Article
Open access
PDF file
HMHlaudi Daniel Masethe
Hlaudi Daniel Masethe
MMMosima Anna Masethe
Mosima Anna Masethe
Sunday Olusegun OjoSunday Olusegun Ojo
Sunday Olusegun Ojo
FGFausto Giunchiglia
Fausto Giunchiglia
POPius Owolawi
Pius 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.

25 March 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HMHlaudi Daniel Masethe
Hlaudi Daniel Masethe
MMMosima Anna Masethe
Mosima Anna Masethe
Sunday Olusegun OjoSunday Olusegun Ojo
Sunday Olusegun Ojo
POPius Owolawi
Pius Owolawi
FGFausto Giunchiglia
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.

22 September 2025 in Computers
Verified
Journal Article
Open access
PDF file
MMMosima Anna Masethe
Mosima Anna Masethe
Sunday Olusegun OjoSunday Olusegun Ojo
Sunday Olusegun Ojo
HMHlaudi Daniel Masethe
Hlaudi Daniel 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.

26 November 2025
Verified
Conference Paper
Closed access
ESEminence Shabangu
Eminence Shabangu
MMMosima Anna Masethe
Mosima Anna Masethe
HMHlaudi Daniel Masethe
Hlaudi Daniel Masethe
ADAlex D. Dandadzi
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.

25 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
HMHlaudi Daniel Masethe
Hlaudi Daniel Masethe
MMMosima Anna Masethe
Mosima Anna Masethe
ZMZamikhaya Mapundu
Zamikhaya Mapundu
POPius Owolawi
Pius Owolawi
MMMichael nthabiseng Moeti
Michael nthabiseng 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.