Purpose: This study aims to investigate factors that could predict the continued usage of e-learning systems, such as the learning management systems (LMS) at a Technical University in Ghana using machine learning algorithms. Design/methodology/approach: The proposed model for this study adopted a unified theory of acceptance and use of technology as a base model and incorporated the following constructs: availability of resources (AR), computer self-efficacy (CSE), perceived enjoyment (PE) and continuance intention to use (CIU). The study used an online questionnaire to collect data from 280 students of a Technical University in Ghana. The partial least square-structural equation model (PLS-SEM) method was used to determine the measurement model’s reliability and validity. Machine learning algorithms were used to determine the relationships among the constructs in the proposed research model. Findings: The findings from the study confirmed that AR, CSE, PE, performance expectancy, effort expectancy and social influence predicted students’ continuance intention to use the LMS. In addition, CIU and facilitating conditions predicted the continuance use of the LMS. Originality/value: The use of machine learning algorithms in e-learning systems literature has been rarely used. Thus, this study contributes to the literature on the continuance use of e-learning systems using machine learning algorithms. Furthermore, this study contributes to the literature on the continuance use of e-learning systems in developing countries, especially in a Ghanaian higher education context.

Despite a few attempts to automatically crawl Ewe text from online news portals and magazines, the African Ewe language remains underdeveloped despite its rich morphology and complex "unique" structure. This is due to the poor quality, unbalanced, and religious-based nature of the crawled Ewe texts, thus making it challenging to preprocess and perform any NLP task with current transformer-based language models. In this study, we present a well-preprocessed Ewe dataset for low-resource text classification to the research community. Additionally, we have developed an Ewe-based word embedding to leverage the low-resource semantic representation. Finally, we have fine-tuned seven transformer-based models, namely BERT-based (cased and uncased), DistilBERT-based (cased and uncased), RoBERTa, DistilRoBERTa, and DeBERTa, using the preprocessed Ewe dataset that we have proposed. Extensive experiments indicate that the fine-tuned BERT-base-cased model outperforms all baseline models with an accuracy of 0.972, precision of 0.969, recall of 0.970, loss score of 0.021, and an F1-score of 0.970. This performance demonstrates the model’s ability to comprehend the low-resourced Ewe semantic representation compared to all other models, thus setting the fine-tuned BERT-based model as the benchmark for the proposed Ewe dataset.

Feature extraction plays a critical role in text classification, as it converts textual data into numerical representations suitable for machine learning models. A key challenge lies in effectively capturing both semantic and contextual information from text at various levels of granularity while avoiding overfitting. Prior methods have often demonstrated suboptimal performance, largely due to the limitations of the feature extraction techniques employed. To address these challenges, this study introduces Multi-TextCNN, an advanced feature extractor designed to capture essential textual information across multiple levels of granularity. Multi-TextCNN is integrated into a proposed classification model named MuTCELM, which aims to enhance text classification performance. The proposed MuTCELM leverages five distinct sub-classifiers, each designed to capture different linguistic features from the text data. These sub-classifiers are integrated into an ensemble framework, enhancing the overall model performance by combining their complementary strengths. Empirical results indicate that MuTCELM achieves average improvements across all datasets in accuracy, precision, recall, and F1-macro scores by 0.2584, 0.2546, 0.2668, and 0.2612, respectively, demonstrating significant performance gains over baseline models. These findings underscore the effectiveness of Multi-TextCNN in improving model performance relative to other ensemble methods. Further analysis reveals that the non-overlapping confidence intervals between MuTCELM and baseline models indicate statistically significant differences, suggesting that the observed performance improvements of MuTCELM are not attributable to random chance but are indeed statistically meaningful. This evidence indicates the robustness and superiority of MuTCELM across various languages and text classification tasks.