Delali Kwasi Dake
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Delali Kwasi Dake has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Bimlesh Wadhwa
National University of Singapore, Singapore, Singapore
2 shared publications - Charles Buabeng-Andoh
Department of ICT Education, University of Education, Winneba, Ghana
2 shared publications - Claudia Szabo
Adelaide University, Adelaide, Australia
2 shared publications - Elijah Ofori
University of Education, Winneba, Ghana
2 shared publications - Esther Gyimah
University of Education
2 shared publications - Griffith Selorm Klogo
Kwame Nkrumah University of Science and Technology, Kumasi, Ghana
2 shared publications
Latest Publications
- 8 April 2026
- Published by MECS Publisher in International Journal of Modern Education and Computer Science
- Vol. 18 (2) , 147-162
Cluster Pattern Analysis of Students Stress using Machine Learning Algorithms with Feature Engineering
Students attending school experience stress due to a variety of factors that can originate either on campus or from home. In managing stress and other related issues, educational institutions now have counselling units that operate as centres. Moreover, several institutions have designated academic counsellors in departments to address the increasing demand for counselling services due to an expanding student population. Timely detection and proactive counselling of stress among students can help avert dropouts, health issues, and other learner behaviours that are detrimental to academic work. This study proposes two approaches to facilitate the automation of student counselling for stress management. We first implemented the K-means algorithm and formed clusters using the elbow and the Silhouette methods. The clusters formed reveal three groups of students. The stressors significantly affected one group, making it vulnerable. The stressors moderately impacted another group, while the final group experiences minimal stress. In the second part of the study, we proposed a classification model to identify the cluster group of any new student. The results of the classification show superior performance for the Decision Tree algorithm with an accuracy of 97.64%. The improvement in the efficiency of the classification algorithms was attained through feature engineering using the Chi-square method.
- 8 April 2026
- Published by MECS Publisher in International Journal of Modern Education and Computer Science
- Vol. 18 (2) , 147-162
Cluster Pattern Analysis of Students Stress using Machine Learning Algorithms with Feature Engineering
Students attending school experience stress due to a variety of factors that can originate either on campus or from home. In managing stress and other related issues, educational institutions now have counselling units that operate as centres. Moreover, several institutions have designated academic counsellors in departments to address the increasing demand for counselling services due to an expanding student population. Timely detection and proactive counselling of stress among students can help avert dropouts, health issues, and other learner behaviours that are detrimental to academic work. This study proposes two approaches to facilitate the automation of student counselling for stress management. We first implemented the K-means algorithm and formed clusters using the elbow and the Silhouette methods. The clusters formed reveal three groups of students. The stressors significantly affected one group, making it vulnerable. The stressors moderately impacted another group, while the final group experiences minimal stress. In the second part of the study, we proposed a classification model to identify the cluster group of any new student. The results of the classification show superior performance for the Decision Tree algorithm with an accuracy of 97.64%. The improvement in the efficiency of the classification algorithms was attained through feature engineering using the Chi-square method.
- Open Access
- 1 January 2026
- Published by EJournal Publishing in International Journal of Information and Education Technology
- Vol. 16 (4) , 1007-1019
From Education to Employment: A Deep Learning Approach to Understanding Job Market Trends in Africa
The research addresses the complex relationship between education and job outcomes in Africa, examining it through a deep learning approach using South Africa’s most recent Quarterly Labour Force Survey (2024). In this study, we developed a Multilayer Perceptron (MLP) model to predict employment and long-term employment status, achieving an accuracy of 99.71% for employment prediction and 91% for long-term unemployed predictions. The use of Local Interpretable Model-Agnostic Explanations (LIME) also helped interpret the model, revealing education level, industry type, job-seeking behavior, and work experience as important predictors. We observed a discrepancy between educational attainment and job-market demands, noting that technical and vocational training plays a crucial role in addressing labor shortages. These findings have important implications for AI-generated employment predictions, supporting the use of data-driven research to inform labor-policy development and workforce planning. Key recommendations include expanding vocational training, aligning educational curricula with current labor-market demands, and developing upskilling programs for workers in transitional careers. Additionally, integrating Artificial Intelligence (AI) tools can improve national labor-market forecasting. This study contributes to promoting a more inclusive and data-driven transition from education to employment across Africa.
- 1 January 2026
- Published by EJournal Publishing in International Journal of Information and Education Technology
- Vol. 16 (4) , 1007-1019
Open AccessFrom Education to Employment: A Deep Learning Approach to Understanding Job Market Trends in Africa
The research addresses the complex relationship between education and job outcomes in Africa, examining it through a deep learning approach using South Africa’s most recent Quarterly Labour Force Survey (2024). In this study, we developed a Multilayer Perceptron (MLP) model to predict employment and long-term employment status, achieving an accuracy of 99.71% for employment prediction and 91% for long-term unemployed predictions. The use of Local Interpretable Model-Agnostic Explanations (LIME) also helped interpret the model, revealing education level, industry type, job-seeking behavior, and work experience as important predictors. We observed a discrepancy between educational attainment and job-market demands, noting that technical and vocational training plays a crucial role in addressing labor shortages. These findings have important implications for AI-generated employment predictions, supporting the use of data-driven research to inform labor-policy development and workforce planning. Key recommendations include expanding vocational training, aligning educational curricula with current labor-market demands, and developing upskilling programs for workers in transitional careers. Additionally, integrating Artificial Intelligence (AI) tools can improve national labor-market forecasting. This study contributes to promoting a more inclusive and data-driven transition from education to employment across Africa.
- Open Access
- 24 December 2025
- Published by Springer Nature in Discover Education
- Vol. 5 (1)
ChatGPT’s benefits, acceptance, and ethical challenges for teaching and learning in key African countries: a systematic review of literature from 2022 to 2024
- 24 December 2025
- Published by Springer Nature in Discover Education
- Vol. 5 (1)
Open AccessChatGPT’s benefits, acceptance, and ethical challenges for teaching and learning in key African countries: a systematic review of literature from 2022 to 2024
- Open Access
- 19 December 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 313
Explainable artificial intelligence in LSTM transformer models for student performance analysis
- 19 December 2025
- Published by Springer Nature in Discover Computing
- Vol. 28 (1) , 313
Open AccessExplainable artificial intelligence in LSTM transformer models for student performance analysis
- Open Access
- 26 November 2025
- Published by Springer Nature in Discover Global Society
- Vol. 3 (1) , 158
Information technology graduates employability prediction model in a low-income country using tree-based machine learning classifiers
- 26 November 2025
- Published by Springer Nature in Discover Global Society
- Vol. 3 (1) , 158
Open AccessInformation technology graduates employability prediction model in a low-income country using tree-based machine learning classifiers
- Open Access
- 21 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 64-106
Ethical and Societal Impacts of Generative AI in Higher Computing Education: An ACM Task Force Working Group to Develop a Landscape Analysis - Perspectives from the Global Souths and Guidelines for CS1/CS2/CS3
- 21 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 64-106
Open AccessEthical and Societal Impacts of Generative AI in Higher Computing Education: An ACM Task Force Working Group to Develop a Landscape Analysis - Perspectives from the Global Souths and Guidelines for CS1/CS2/CS3
- Open Access
- 21 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 371-372
Ethical and Societal Impacts of Generative AI in Higher Computing Education: An ACM Task Force Working Group to Develop a Landscape Analysis - Perspectives from the Global Souths and Guidelines for CS1/CS2/CS3
- 21 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 371-372
Open AccessEthical and Societal Impacts of Generative AI in Higher Computing Education: An ACM Task Force Working Group to Develop a Landscape Analysis - Perspectives from the Global Souths and Guidelines for CS1/CS2/CS3
- Open Access
- 1 January 2025
- Published by Informing Science Institute in Informing Science: The International Journal of an Emerging Transdiscipline
- Vol. 28, 024
Using Machine Learning Algorithms to Cluster and Analyse Students’ Acceptance of Mobile Learning Management Systems
Aim/Purpose Technology adoption and utilization in educational institutions have increased since the pandemic. Recently, the learning management system has become crucial in the educational sector, enabling the efficient execution of online learning. In this study, we performed clustering on group learners to understand students’ concerns with the mobile Learning Management System (m-LMS) based on the clusters. Furthermore, we employed classification using the technology acceptance model to evaluate the correlation among factors necessitating the acceptance and use of m-LMS. Background Mobile learning (m-learning) is a prevalent method of education where educational content is accessed on the go via mobile devices such as smartphones and tablets. The acceptance and deployment of mobile learning in higher education institutions has become essential in Education 4.0, a reskilling approach associated with Industry 4.0. Since the pandemic, mobile learning management systems have seen increased usage among educational institutions. Methodology The study modified the standard data mining and knowledge discovery methodology. This study’s data set includes 446 students from the University of Education, Winneba, Ghana. The K-means algorithm was implemented to determine the number of clusters from the dataset according to the features. Subsequently, we employed a Pearson correlation coefficient heatmap to ascertain the predictability of perceived ease of use, perceived usefulness, attitude towards using, and actual system use of the features via the technology acceptance model. Then, a classifier was built by comparing five classification algorithms. Contribution A novel study on the application of a machine learning algorithm for a mobile learning management system dataset in Ghana. Implementing K-means, heatmap, and feature selection to understand learners’ concerns while using m-LMS in Ghana. Findings The findings indicate that Cluster 1 members disagree with the benefits of using m-LMS. The disagreement cuts across all the investigated variables: perceived usefulness, perceived ease of use, attitude toward using, and actual use. Cluster 2 members agree strongly with the benefits of using m-LMS across all the investigated variables. Cluster 0, with the highest number of members, moderately agrees with the benefits of using m-LMS. In addition, a strong correlation exists between perceived ease of use, perceived usefulness, and attitude towards using. Furthermore, the attitude towards using was predicted by perceived usefulness. However, there was an unreliable relationship between attitude towards using and actual system use. Recommendations for Practitioners Cluster segmentation of students using m-LMS facilitates the formulation of an implementation policy, enabling educational authorities to address the issues contributing to student dissatisfaction with m-LMS. Furthermore, the results imply that, even though students desire to use a mobile learning management system, they are not using it. It means there are challenges surrounding using the mobile learning management system at the University of Education, Winneba. Recommendations for Researchers The use of K-means, elbow function, and correlation heatmap in the technology acceptance model for variable correlation test reveals detailed predictability patterns that necessitate a new research direction using machine learning. Impact on Society Stakeholders in education should embrace and support machine learning implementation in the educational sector to reveal data patterns for improved teaching and learning. Future Research Subsequent research will broaden the data on mobile learning management systems to include the majority of tertiary institutions in Ghana. The data will be indicative, allowing for the generalisation of inferences regarding national policy directions on m-LMS.
- 1 January 2025
- Published by Informing Science Institute in Informing Science: The International Journal of an Emerging Transdiscipline
- Vol. 28, 024
Open AccessUsing Machine Learning Algorithms to Cluster and Analyse Students’ Acceptance of Mobile Learning Management Systems
Aim/Purpose Technology adoption and utilization in educational institutions have increased since the pandemic. Recently, the learning management system has become crucial in the educational sector, enabling the efficient execution of online learning. In this study, we performed clustering on group learners to understand students’ concerns with the mobile Learning Management System (m-LMS) based on the clusters. Furthermore, we employed classification using the technology acceptance model to evaluate the correlation among factors necessitating the acceptance and use of m-LMS. Background Mobile learning (m-learning) is a prevalent method of education where educational content is accessed on the go via mobile devices such as smartphones and tablets. The acceptance and deployment of mobile learning in higher education institutions has become essential in Education 4.0, a reskilling approach associated with Industry 4.0. Since the pandemic, mobile learning management systems have seen increased usage among educational institutions. Methodology The study modified the standard data mining and knowledge discovery methodology. This study’s data set includes 446 students from the University of Education, Winneba, Ghana. The K-means algorithm was implemented to determine the number of clusters from the dataset according to the features. Subsequently, we employed a Pearson correlation coefficient heatmap to ascertain the predictability of perceived ease of use, perceived usefulness, attitude towards using, and actual system use of the features via the technology acceptance model. Then, a classifier was built by comparing five classification algorithms. Contribution A novel study on the application of a machine learning algorithm for a mobile learning management system dataset in Ghana. Implementing K-means, heatmap, and feature selection to understand learners’ concerns while using m-LMS in Ghana. Findings The findings indicate that Cluster 1 members disagree with the benefits of using m-LMS. The disagreement cuts across all the investigated variables: perceived usefulness, perceived ease of use, attitude toward using, and actual use. Cluster 2 members agree strongly with the benefits of using m-LMS across all the investigated variables. Cluster 0, with the highest number of members, moderately agrees with the benefits of using m-LMS. In addition, a strong correlation exists between perceived ease of use, perceived usefulness, and attitude towards using. Furthermore, the attitude towards using was predicted by perceived usefulness. However, there was an unreliable relationship between attitude towards using and actual system use. Recommendations for Practitioners Cluster segmentation of students using m-LMS facilitates the formulation of an implementation policy, enabling educational authorities to address the issues contributing to student dissatisfaction with m-LMS. Furthermore, the results imply that, even though students desire to use a mobile learning management system, they are not using it. It means there are challenges surrounding using the mobile learning management system at the University of Education, Winneba. Recommendations for Researchers The use of K-means, elbow function, and correlation heatmap in the technology acceptance model for variable correlation test reveals detailed predictability patterns that necessitate a new research direction using machine learning. Impact on Society Stakeholders in education should embrace and support machine learning implementation in the educational sector to reveal data patterns for improved teaching and learning. Future Research Subsequent research will broaden the data on mobile learning management systems to include the majority of tertiary institutions in Ghana. The data will be indicative, allowing for the generalisation of inferences regarding national policy directions on m-LMS.
- Open Access
- 8 August 2023
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 3 (1) , 1-22
Instructor-assisted question classification system using machine learning algorithms with N-gram and weighting schemes
One aspect of natural language processing, text classification, has become necessary in the educational domain due to the increasing number of students and the COVID-19 outbreak. The advent of the devastating pandemic and the need to remain safe have surged the discussions around online learning and integrated modules in teaching and learning. In this study, we employed machine learning to develop an automatic instructor-assisted question classification module for learning management systems. In selecting the best classifier, the conventional and the ensemble machine learning algorithms were compared using the tenfold and the fivefold cross-validation techniques. In addition, the N-gram feature selection mechanism and three weighting schemes were evaluated for performance enhancement. The detailed analysis indicates that the ensemble algorithms outperform the conventional ones with decreasing accuracy as the N-gram size increases. For all compared algorithms, the AdaBoost (SVM) ensemble algorithm has the highest accuracy of 78.55% for Unigram (TP, TF, TF-IDF). In addition, the AdaBoost (SVM) emerged with the highest F1-score of 0.782, whiles the ensemble Bagging (RF) algorithm had the highest ROC value of 0.955 for Unigram (TP).
- 8 August 2023
- Published by Springer Nature in Discover Artificial Intelligence
- Vol. 3 (1) , 1-22
Open AccessInstructor-assisted question classification system using machine learning algorithms with N-gram and weighting schemes
One aspect of natural language processing, text classification, has become necessary in the educational domain due to the increasing number of students and the COVID-19 outbreak. The advent of the devastating pandemic and the need to remain safe have surged the discussions around online learning and integrated modules in teaching and learning. In this study, we employed machine learning to develop an automatic instructor-assisted question classification module for learning management systems. In selecting the best classifier, the conventional and the ensemble machine learning algorithms were compared using the tenfold and the fivefold cross-validation techniques. In addition, the N-gram feature selection mechanism and three weighting schemes were evaluated for performance enhancement. The detailed analysis indicates that the ensemble algorithms outperform the conventional ones with decreasing accuracy as the N-gram size increases. For all compared algorithms, the AdaBoost (SVM) ensemble algorithm has the highest accuracy of 78.55% for Unigram (TP, TF, TF-IDF). In addition, the AdaBoost (SVM) emerged with the highest F1-score of 0.782, whiles the ensemble Bagging (RF) algorithm had the highest ROC value of 0.955 for Unigram (TP).
- Open Access
- 1 January 2023
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2023 (1)
University Students Behaviour Modelling Using the K‐Prototype Clustering Algorithm
Counselling students remains a pre‐eminence for most tertiary institutions in Ghana to the extent that institutions now have counselling units that extend to the departmental level. This study used the K‐prototype machine learning algorithm to cluster students’ behaviour based on 28 relevant attributes and further proposed a classification model. The analysis of the experimental outcomes using the elbow method reveals the formation of three distinct clusters with decreasing intra‐cluster similarities and increasing inter‐cluster distances. The first cluster uniquely consists of active learners with three or more roommates, primarily in the first year. The second cluster with the highest membership consists mainly of second‐year students who exhibit passive classroom conduct and reside in a two‐occupancy hostel. The third cluster contains a mixture of third and final‐year students who are highly passive in class and live in a tenancy occupancy of two. After clustering, the K‐nearest neighbours, logistic regression, naïve Bayes (NB), and AdaBoost ensemble algorithms were implemented to create a model for future learner cluster prediction. Simulation results using the tenfold cross‐validation technique show that AdaBoost (NB) has the highest accuracy of 99.88% with an F‐measure score of 0.999 and receiver operating characteristic–area under the curve value of 1.00.
- 1 January 2023
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2023 (1)
Open AccessUniversity Students Behaviour Modelling Using the K‐Prototype Clustering Algorithm
Counselling students remains a pre‐eminence for most tertiary institutions in Ghana to the extent that institutions now have counselling units that extend to the departmental level. This study used the K‐prototype machine learning algorithm to cluster students’ behaviour based on 28 relevant attributes and further proposed a classification model. The analysis of the experimental outcomes using the elbow method reveals the formation of three distinct clusters with decreasing intra‐cluster similarities and increasing inter‐cluster distances. The first cluster uniquely consists of active learners with three or more roommates, primarily in the first year. The second cluster with the highest membership consists mainly of second‐year students who exhibit passive classroom conduct and reside in a two‐occupancy hostel. The third cluster contains a mixture of third and final‐year students who are highly passive in class and live in a tenancy occupancy of two. After clustering, the K‐nearest neighbours, logistic regression, naïve Bayes (NB), and AdaBoost ensemble algorithms were implemented to create a model for future learner cluster prediction. Simulation results using the tenfold cross‐validation technique show that AdaBoost (NB) has the highest accuracy of 99.88% with an F‐measure score of 0.999 and receiver operating characteristic–area under the curve value of 1.00.