Non-computing students often encounter greater challenges in programming courses compared to their computing counterparts, primarily stemming from a lack of motivation in the subject. Motivation plays a pivotal role in the success of introductory programming (IP) modules, with intrinsically and extrinsically motivated students exhibiting greater enjoyment and engagement in learning activities. While numerous studies have attempted to enhance motivation in IP modules, most have focused on computing students which is influenced lar gely by the constructivist theory. This paper addresses this gap by proposing a cognitive-based teaching framework aimed at bolstering motivation among non-computing students. The proposed approach employs the Explicit Instruction paradigm, where the instructor first designs learning strategies and provides students with detailed explanations, demonstrations, examples, and non-examples. This enables the students to apply the strategies in groups, practice with feedback, and finally individually. The effectiveness of this approach was assessed using first-year students at two universities, one in South Africa and the other in Cameroon. We collected student motivation data using a quantitative questionnaire post-experiment. The results indicate that the proposed teaching method had a positive impact on participant motivation in terms of attendance, perceived relevance, confidence, and satisfaction. However, the specific degree of improvement varied among the participants.

At present, education is a matter of global concern and it is the responsibility of all States to be able to provide the ideal conditions so that it is accessible to the entire population. As indicated by one of the objectives of the 2030 Agenda which seeks to guarantee inclusive and equitable education quality. Different studies indicate that instructional design models allow the creation of optimal educational environments for all people and that their correct application allows students to generate satisfactory learning, however, there is an important group of people who are not considered in the tests of these models making it is impossible to reach the goal of achieving the desired educational inclusion. Therefore, the stated objective is to demonstrate that people with some type of disability have not been considered to work and to validate the studies that use different models, approaches or techniques to develop virtual learning environments. The results are worrisome as they demonstrate that of the 90 scientific articles analyzed, only 4.44% have included topics related to disability and of the total sample of participants that total 11,732 people, only 42, that is, 0.36%, had some type of disability. This shows that we are very far from being able to meet the sustainable development goal that seeks to guarantee inclusive and equitable quality education. Based on the results achieved, it is intended to sensitize governments, educational institutions and teachers around the world to work responsibly to close the gap that marginalizes people with disabilities and build appropriate virtual learning environments that guarantee that everyone can access and learn in the best way.

In the work, an analysis of modern methods of Educational Data Mining (EDM) was carried out, on the basis of which a set of methods of EDM was developed for the training of vocational education teachers. The basic methods of EDM are considered, namely Prediction, Clustering, Relationship Mining, Distillation of Data for Human Judgment, Discovery with Models. The possibilities of using artificial neural networks, in particular, networks of Long-Short-Term Memory (LSTM), to predict the results of the educational process are described. The main methods of clustering and segmentation of educational data are considered. The basic methods of EDM are complemented by specialized methods of digital image pre-processing and methods of artificial intelligence, taking into account the peculiarities of the training of future specialists in engineering and pedagogical specialties. As specialized methods of digital image pre-processing, methods of filtering, contrast enhancement and contour selection are used. As specialized methods of artificial intelligence, methods of image segmentation, object detection on images, object detection using fuzzy logic were used. Methods of object detection on images using convolutional neural networks and using the Viola-Jones method are described. To process data with a certain degree of uncertainty, it is proposed to apply the methods of EDM and Fuzzy Logic in a integral manner. Ways of integrating Fuzzy Logic with methods of data clustering, image segmentation and object detection on images are considered. The possibilities of applying the developed complex of specialized methods of EDM in the educational process, in particular, when performing STEM (Science, Technology, Engineering and Mathematics) projects, are described.

Aiming at the problems of large information loss and feature loss in the similarity design of high-dimensional panel data in clustering, a new panel data clustering method was proposed, which named an adaptive clustering method for panel data based on multi-dimensional feature extraction. This method defined "comprehensive quantity", "absolute quantity", "growth rate", "general trend" and "fluctuation quantity" of samples to extract features, and the five features were weighted to calculate the samples comprehensive distance. On this basis, ward method is used for clustering. This method can greatly reduces the loss of effective information. To verify the effectiveness of the method, cluster empirical analysis was conducted using GDP panel data from 31 regions in China, and the clustering results were compared with those of other clustering models. The experimental results showed that the proposed model was more interpretable and the clustering results were better.

Student academic performance (SAP) prediction is a key issue in education data analysis. Also, the assessment of students’ performance is used to enhance the efficiency of educational institutions. With the development in educational institutions and modern technology, focusing on the academic performance prediction of the student based on access to the smartphone is the need of the hour. To improve the accuracy of student academic performance prediction, the Canberra Match Normalization-based Generalized Canonical Correlative Decision Stump Classifier (CMN-GCCDSC) is introduced. Initially, student data are collected from the dataset. After the data collection process, the proposed CMN-GCCDSC technique is applied in two phases namely data preprocessing and classification respectively. In the first phase, data preprocessing is carried out to eliminate duplicate data using the Canberra Match Data Normalization technique to minimize space and time consumption. In the second phase, data classification is performed with preprocessed output to classify student academic performance using a generalized canonical correlative decision stump classifier based on Smartphone addiction prediction. The generalized canonical correlation analysis is used for decision-making. Based on analysis, student academic performance is classified and results are obtained. An experimental assessment of the proposed CMN-GCCDSC technique and existing methods is carried out with metrics such as accuracy, sensitivity, specificity, space complexity, and time complexity. The CMN-GCCDSC technique is an effective solution that addresses the limitations of Genetic Algorithm (GA)-based decision tree classifiers. By combining the Decision Stump Classifier (DSC) approach with Generalized Canonical Correlation (GCC), the most important feature to consider for academic prediction among students can be selected, ultimately reducing the dimensionality of the dataset, and improving classifier performance. With higher accuracy rates achieved, this technique can help identify at-risk students early and discover hidden trends and patterns in student performance, leading to improved academic outcomes with additional support from institutions and faculties.

In recent years, the widespread use of social networks has empowered online users to freely share their opinions on diverse aspects of life. Sentiment Analysis (SA) has consequently emerged as a pivotal domain within Natural Language Processing (NLP), serving a crucial role in discerning sentiment orientations and extracting valuable insights from public viewpoints. Analyzing sentiment in Arabic poses distinctive challenges due to its varied dialects, as well as its intricate morphological and syntactic structures. Deep Learning (DL) models, particularly Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs), have exhibited remarkable proficiency in Sentiment Analysis. LSTM networks excel in capturing sequential data patterns, while CNNs offer inherent advantages in feature selection, yielding superior performance compared to conventional machine learning (ML) algorithms. In our study, we propose an ensemble approach that integrates CNN and LSTM techniques to classify and forecast sentiment in tweets. We evaluate the effectiveness of this hybrid model against individual LSTM and CNN methodologies employing the FastText word embedding model. Experimental findings illustrate that our LSTM-CNN hybrid approach, leveraging the FastText word embedding model, significantly improves text classification accuracy.

Customer attrition is a major issue that affects the telecom industry as it reduces the company’s revenues and the overall customer base. Solving this problem involves the use of accurate prediction models that utilize CRM data and machine learning algorithms. Though several research papers have been written and published on CCP in the telecom industry, the existing models lack reliability and accuracy. The use of sophisticated data mining and machine learning techniques has been widely practised for improving predictive models. Churn prediction models that exist have their problems in terms of accuracy and errors. It is still important to develop more sophisticated models that can work well with large data and give accurate predictions. Therefore, this work aims to offer the OKMSVM model for  multiclass cancer-type classification. The method applied for the dimensionality reduction pre-process is Kernel Principal Component Analysis (KPCA) and the feature selection pre-process is done using Ant Lion Optimization (ALO). This combination assists in improving the chance of the prediction and also the reduction of probable errors. The performance of the proposed OKMSVM model was compared with some of the most common churn prediction models such as HTLSVM, DNN, ICPCSF and other ML models. It was seen that the OKMSVM model outperformed other models with an accuracy of 91. 5%, an AUC of 85. Accurate, with a correlation coefficient of 0. 838. It further shows that this model is better than the current models in the market in estimating customer churn.