Diabetic ketoacidosis (DKA) is a serious complication that affects millions of individuals globally and presents significant health complications. Hyperchloremia, an electrolyte imbalance characterized by high levels of chloride in the blood, may result in gastrointestinal problems, kidney damage, and even death, especially in DKA patients. Early detection and treatment of hyperchloremia are of utmost importance in the management of DKA. This study explores the potential of the bootstrap aggregating ensemble with random subspaces machine learning approach to predict the occurrence of hyperchloremia, providing a basis for early intervention and improved patient outcomes. We tested our approach with the retrospective MIMIC-III database containing 1177 DKA patients and compared it with previous studies with an area under the curve (AUC) of 100%. Our approach showed significant performance outperforming other methods. The combination of this approach may enhance the early detection and timely intervention of hyperchloremia cases, ultimately leading to improved patient outcomes and a more effective management of DKA-associated complications. Our work aims to contribute to the development of decision support tools for healthcare professionals, assisting them in making informed decisions for DKA patients, with a focus on preventing and managing hyperchloremia.

Sentiment analysis is a crucial tool for measuring public opinion and understanding human communication across digital social media platforms. However, due to linguistic complexities and limited data or computational resources, it is under-represented in many African languages. While state-of-the-art Afrocentric pre-trained language models (PLMs) have been developed for various natural language processing (NLP) tasks, their applications in eXplainable Artificial Intelligence (XAI) remain largely unexplored. In this study, we propose a novel approach that combines Afrocentric PLMs with XAI techniques for sentiment analysis. We demonstrate the effectiveness of incorporating attention mechanisms and visualization techniques in improving the transparency, trustworthiness, and decision-making capabilities of transformer-based models when making sentiment predictions. To validate our approach, we employ the SAfriSenti corpus, a multilingual sentiment dataset for South African under-resourced languages, and perform a series of sentiment analysis experiments. These experiments enable comprehensive evaluations, comparing the performance of Afrocentric models against mainstream PLMs. Our results show that the Afro-XLMR model outperforms all other models, achieving an average F1-score of 71.04% across five tested languages, and the lowest error rate among the evaluated models. Additionally, we enhance the interpretability and explainability of the Afro-XLMR model using Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP). These XAI techniques ensure that sentiment predictions are not only accurate and interpretable but also understandable, fostering trust and reliability in AI-driven NLP technologies, particularly in the context of African languages.

The existence of diverse traditional machine learning and deep learning models designed for various multimodal music information retrieval (MIR) applications, such as multimodal music sentiment analysis, genre classification, recommender systems, and emotion recognition, renders the machine learning and deep learning models indispensable for the MIR tasks. However, solving these tasks in a data-driven manner depends on the availability of high-quality benchmark datasets. Hence, the necessity for datasets tailored for multimodal music information retrieval applications is paramount. While a handful of multimodal datasets exist for distinct music information retrieval applications, they are not available in low-resourced languages, like Sotho-Tswana languages. In response to this gap, we introduce a novel multimodal music information retrieval dataset for various music information retrieval applications. This dataset centres on Sotho-Tswana musical videos, encompassing both textual, visual, and audio modalities specific to Sotho-Tswana musical content. The musical videos were downloaded from YouTube, but Python programs were written to process the musical videos and extract relevant spectral-based acoustic features, using different Python libraries. Annotation of the dataset was done manually by native speakers of Sotho-Tswana languages, who understand the culture and traditions of the Sotho-Tswana people. It is distinctive as, to our knowledge, no such dataset has been established until now.

Music genre classification is a fundamental task within the domain of music information retrieval, aimed at discerning the categorical placement, or genre, of a given musical piece. Such classification holds significant utility in facilitating music recommendations tailored to individual preferences. Traditionally, efforts in music genre classification have primarily concentrated on unimodal analyses, focusing either on textual (lyrics) or audio components of music. However, given that music communicates through multiple modalities, including lyrics, audio, and visuals, there exists a pressing need to integrate these diverse sources of information. Multimodal music genre classification thus emerges as a solution, leveraging the amalgamation of two or more modalities present in music production to discern genre categorizations effectively. Moreover, existing endeavors in music genre classification have predominantly centered on compositions in Western languages, with comparatively limited attention devoted to non-Western languages. This study addresses these gaps by employing deep learning and language models to undertake multimodal music genre classification specifically within the context of Sotho-Tswana musical videos. The findings of this study demonstrate the efficacy of multimodal music genre classification, showcasing superior performance compared to unimodal approaches relying solely on lyrics for genre classification.

Does race bias manifest in South African news, and how can computational methods like word embeddings reveal it? After apartheid’s end in 1994, South

Word embeddings have become powerful tools for detecting social biases encoded in language, yet research on measuring race bias through embeddings remains underdeveloped compared to studies on gender bias. This gap largely stems from the complexity of constructing race dimensions, which involve socially contested meanings and less clear semantic oppositions. Existing studies on race bias often rely on intuition and context-specific approaches when choosing anchor terms. In this paper, we address this methodological gap by providing statistical metrics to evaluate the quality and adaptability of race categories in embeddings. We apply these metrics to race categories across three embeddings—Google News (U.S.-centric), South African News (South African context), and Wikipedia (neutral, general-purpose). We find that names are effective for constructing race dimensions, with sub-Saharan African/European name categories producing more stable and generalisable dimensions than other categories, while American names were less generalisable. Validation shows that SSA/European name embeddings correlate most strongly with human ratings and demonstrate that our metrics capture human-perceived semantic structure of race. This research provides a framework for constructing robust race dimensions for measuring race bias in word embeddings.