FIGURE 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
Source publication
During the Coronavirus pandemic, e-learning systems have proven to be an essential pillar for education. This raises to surface what many studies have addressed earlier; creating a platform that completes the traditional classroom work and maximizes the effectiveness of learning outcomes. Striving to achieve such platform, studies have considered g...
Citations
... There are many reasons for using video conferencing tools as a teaching and learning modality. Literature reveals that video conferencing improves students' academic performance (García and Vidal, 2019;Sufyan, et al., 2020) and is an effective tool for learning (Maher, Moussa and Khalifa, 2020). Students also reported being comfortable with video conferencing tools, and they were motivated in their virtual classes (Rio-Chillcce, Jara-Monge and Andrade-Arenas, 2021). ...
... However, issues have been identified in using video conferencing platforms, such as subjects requiring laboratory work (Rahim, et al., 2020), network connection and speed, and self-conscious behavior (Maher, Moussa and Khalifa, 2020). Some educators still face psychological challenges due to the new teaching modality (Rio-Chillcce, Jara-Monge and Andrade-Arenas, 2021) and have to attend training on using these new digital tools to overcome psychological issues. ...
The usage of video conferencing tools in teaching and learning has become a norm in today's higher educational institutions, recognized across various academic settings. The experience gained by most educators in using video conferencing tools for teaching during the COVID-19 pandemic could be leveraged to enhance these tools. The study aims to capture the current practices and explore the issues of using video conferencing for teaching and learning in Malaysian higher educational institutions. It focuses on three target groups with hands-on experience: academicians, students, and e-learning consultants or information technology (IT) support staff. Interview and focus group protocols were developed based on the four elements of the PACT framework: People (P), Activities (A), Contexts (C), and Technologies (T). Data were gathered through focus group discussions and in-depth interviews with the target groups. There were 24 participants involved in three focus group discussions and 28 participants in individual in-depth interviews. The PACT framework was employed to analyze the data, aiding in understanding the current situation, identifying areas for improvement, and envisioning future scenarios. Qualitative data were transcribed and categorized based on the four PACT elements. The study identified differences in the People element with four scenarios/practices on physical differences, six on psychological differences, three on mental models, and five on social differences. A total of twenty differences were identified under the Activities element, with six on temporal aspects, four each on cooperation, complexity, and safety-critical aspects, and two on the nature of the content. Under the Context element, one scenario/practice was identified for organizational circumstances, five for social circumstances, and three for physical circumstances. In the Technology element, five scenarios/practices were identified: two related to the input part of technologies and one each for the output, communication, and content parts of technologies. From the scenarios/practices of the responses, a total of fifty-two issues related to using video conferencing for teaching and learning were identified. These findings will serve as the basis for ideation in developing innovative video conferencing toolkits for teaching and learning.
... Maher et al., 2020;Missaoui & Maalel, 2021). They tailored digital gamification according to students' 569 user profiles that were determined based on both their static and dynamic information. ...
The systematic review examined research on tailored digital gamification for learning based on 43 peer-reviewed articles published between 2013 and 2022. The study aimed to investigate tailored approaches and game elements, contributing to the use of tailored digital gamification in educational settings. The tailored approaches were categorized as personalization, adaptation, and recommendation, with user modeling as their basis. Five clusters of game elements were employed when using these tailored approaches in digital gamified classes. The findings imply that most of the articles in this review were still in the stage of class preparation and focused on what information can be used to tailor. More empirical studies need to be conducted to examine the motivating effects of tailored digital gamifying classes, using the approaches of personalization, adaptation, and recommendation. Additionally, twenty-three game elements were found in this review study, among which reward was the most often used. Then these game elements were grouped into five clusters based on their functions, that is, performance, personal, social, ecological, and fictional cluster. A variety of game element clusters reflect multiple aspects of gamification. The use of them in each tailored approach might contribute to a better understanding and selection of game elements when tailoring digital gamification. These findings provide a holistic picture of common approaches and related game elements in tailored digital gamifying classes. Teachers and curriculum designers can benefit from this study by considering appropriate approaches and game elements.
... However, some studies have also shown that the effectiveness of gamification is influenced by proper design and implementation. According to Maher et al. [27], the development of gamification in online learning should consider personalization approaches and adaptation of additional gamification elements, such as feedback and evaluation of learning. ...
Online learning has become a trend in today’s digital age. Accessibility, flexibility, a wide variety of learning resources, collaboration and communication, and the use of technology and innovation are reasons for the increasing popularity of online learning. However, student engagement is often low and requires innovative solutions to increase it. This study aims to develop and analyze the effectiveness of gamified Learning Management Systems (LMS) in increasing student engagement in online learning. The research method used is the ADDIE model, which consists of Analysis, Design, Development, Implementation, and Evaluation. The subjects of this study were students of one of the private universities in Indonesia who attended online lectures during the pandemic. Data collected using questionnaires, observation sheets, and interview guidelines were then analyzed using descriptive statistics. The results showed that gamified Learning Management Systems (LMS) was able to increase student engagement in online learning. However, technical limitations and inadequate institutional support were barriers to implementing gamified LMSs. In conclusion, developing gamified LMS can be an effective alternative strategy to increase student engagement in online learning and positively influence their academic performance. Overall, this research contributes to the development of gamified LMS in Indonesia and provides insight into the effectiveness of gamification strategies in increasing student engagement in the online learning environment.
... Game Learning Analytics (GLA) is a branch of the LA field that analyzes data from educational games, with the main focus being evaluating learning outcomes (Freire et al., 2016). Although GLA is primarily focused on serious games, some researchers (Klock et al., 2018;Maher et al., 2020) have explored the use of data from gamified systems. For example, Klock et al. (2018) presented the use of LA techniques incorporated into a gamified environment based on game elements implemented within the system, such as points, challenges, leaderboards, and donations. ...
... The techniques enabled students to visualize their progress and performance to increase user satisfaction and engagement. Following the customization approach, Maher et al. (2020) demonstrated how LA techniques were applied to adapt gamification to the preferences of individual students, i.e., the content was designed and reorganized to meet the individual needs of each student. ...
Introductory computing courses have a high failure rate worldwide. At the Federal University of Amazonas, this also happens and, since 2016 a group of professors decided to reformulate the course at the institution and some learning analytics initiatives have been adopted. The reformulation included a review of the course program and the use of an online judge. After all these years of research, the group has enough material and data and it is a good moment to summarize what has been done and the achievements so far. In this article, the focus will be the learning analytics in three main areas: student performance prediction, classification of difficulty of programming exercises, and gamification. Also, as a contribution, for the first time in a journal, the whole dataset is available to the community.
... The PAGE (Personalized Adaptive Gamified E-learning) model is used to extend MOOCs by providing new levels of learning analytics and visualizations in the learning process, used to customize and adapt educational materials based on those understandings, as well as visualizing the process and adaptation decisions to the learners. It is divided in three modules: course design module; personalized gamified learning flow module; and learning analytics and personalized adaptation module (Maher et al., 2020). GaDeP framework Klemke et al. (2020) The GaDeP framework (Gamification Design Process) is a framework designed to specifically address the lack of theoretical soundness and the missing support of empirical evaluation of the gamification design. ...
Gamification has the potential to enhance learner motivation and increase participation, thereby improving MOOC’s retention rates. However, challenges exist in finding the balance between learning and gamification elements and ensuring effective implementation, as well as the limited availability of established gamification frameworks tailored for MOOCs. The purpose of this review is to shed light on the current state of research, identify research gaps and answer them. The findings underscore the importance of finding a balance in gamification design with game elements’ use, addressing implementation challenges, MOOC platforms, and developing tailored frameworks for MOOCs to optimize learner engagement and retention rates.
... Progress tracking techniques such as progress bars, skill trees, or visual representations assist learners in seeing their progress and providing a sense of success [35]. • Gamified Learning Analytics combines learning analytics [48] with gamification [49]. It collects data from learners' interactions with gamified programming environments to gather insights into their learning habits, progress, and areas for growth. ...
This paper is poised to inform educators, policy makers and software developers about the untapped potential of PWAs in creating engaging, effective, and personalized learning experiences in the field of programming education. We aim to address a significant gap in the current understanding of the potential advantages and underutilisation of Progressive Web Applications (PWAs) within the education sector, specifically for programming education. Despite the evident lack of recognition of PWAs in this arena, we present an innovative approach through the Framework for Gamification in Programming Education (FGPE). This framework takes advantage of the ubiquity and ease of use of PWAs, integrating it with a Pareto optimized gamified programming exercise selection model ensuring personalized adaptive learning experiences by dynamically adjusting the complexity, content, and feedback of gamified exercises in response to the learners’ ongoing progress and performance. This study examines the mobile user experience of the FGPE PLE in different countries, namely Poland and Lithuania, providing novel insights into its applicability and efficiency. Our results demonstrate that combining advanced adaptive algorithms with the convenience of mobile technology has the potential to revolutionize programming education. The FGPE+ course group outperformed the Moodle group in terms of the average perceived knowledge (M = 4.11, SD = 0.51).
... Goal clarity had the highest mean of 3.63 while, (2021) that educational serious games are frequently presented to students by their teachers, directing them to play rather than play willingly. As Maher et al. (2020) observe, gamification concept has recently been considered to motivate and engage learners to maximize learning outcomes. ...
One of the hardest courses for students to grasp is mathematics, yet it’s a crucial ability to have. In order to figure out why students behave in a certain way when studying mathematics, researchers must look for the factors that influence their behaviors. This study helped by presenting the Grade 6 students’ learning behaviors in mathematics and their enjoyment of e-learning games. With thirty (30) grade six students as respondents to the adapted-modified survey questionnaire, the study’s objectives for the academic year 2021–2022 were successfully met through the descriptive-correlational research design and purposive sampling technique. The findings demonstrate a positive significant relationship between interest, confidence, motivation, and usefulness that is consistent with students’ learning behavior in mathematics and the enjoyment of e-learning games in terms of concentration, goal clarity, feedback, challenge, autonomy, immersion, social interaction, and knowledge improvement. Findings showed that e-learning games were helpful at increasing students’ interest in the subject. This means that using e-learning games as a good teaching tool can help to enhance and enhance students’ learning behavior. Taking into account the limitations on a specific subject, the study suggests further scrutiny on the enjoyment of e-Learning games as applied in other disciplines.
... Several approaches were proposed to develop recommender systems, which provoke recommendations to their users as per certain criteria that meet their preferences (Isinkaye et al., 2015;Jumaa et al., 2017;Maher et al., 2020;Moussa et al., 2020). However, these approaches make the prediction process fits a specific domain and dataset complexity. ...
Academic advising is inhibited at most of the high schools to help students identify appropriate academic pathways. The choice of a career domain is significantly influenced by the complexity of life and the volatility of the labor market. Thus, high school students feel confused during the shift period from high school to university, especially with the enormous amounts of data available on the Web. In this paper, an extensive comparative study is conducted to investigate five approaches of recommender systems for university study field and career domain guidance. A novel ontology is constructed to include all the needed information for this purpose. The developed approaches considered user-based and item-based collaborative filtering, demographic-based recommendation, knowledge base supported by case-based reasoning, ontology, as well as different hybridizations of them. A case study on Lebanese high school students is analyzed to evaluate the effectiveness and efficiency of the implemented approaches. The experimental results indicate that the knowledge-based hybrid recommender system, combined with the user-based collaborative filtering and braced with case-based reasoning as well as ontology, generated 98% of similar cases, 95% of them are personalized based on the interests of the high school students. The average usefulness feedback and satisfaction level of the students concerning this proposed hybrid approach reached 95% and 92.5% respectively, which could be a solution to similar problems, regardless of the application domain. Besides, the constructed ontology could be reused in other systems in the educational domain.
... Also, LA encompasses broader components of other disciplines such as EDM, academic analytics, learning sciences, cognitive sciences, human factors, psychology, and so on. Maher et al.[68] proposed a Personalized Adaptive Gamified E-learning (PAGE) model to enhance MOOCs LA and visualization in the learning process. The PAGE model helped learners in learning adaptation and visualization. ...
In recent years, the development of information and communication technology (ICT)-based tools has facilitated human work and increased productivity in solving complex tasks. Computer programming has become an indispensable skill in ICT development because of its wide range of applications. At the same time, meeting the growing demand of highly skilled programmers in the ICT sector is one of the biggest challenges. However, learning programming is not an easy and trivial task, because of programming skills are essentially acquired through repeated practice. Here online judge (OJ) systems provide uninterrupted programming learning and practice opportunities in addition to classroom-based learning. Thus, OJ systems have been adopted by many institutions as an academic tool for programming education, and as a result, a huge number of programming-related resources (source codes, logs, scores, activities, etc.) are regularly accumulated in OJ systems. In this dissertation, we leveraged a large number of real-world source codes, submission logs and scores collected from an OJ system for comprehensive data analysis, as well as training, validation, testing and experimentation with machine learning models for code assessment and classification. First, we analyzed the different features and programming-related problems using a real dataset. We identified various programming errors, including time limit exceeded, memory limit exceeded, runtime error, and presentation errors in solution codes, as well as the impact of programming skills on academic performance. Next, we developed machine learning-based source code assessment and classification models to better understand the programming code and reduce errors. Finally, the outcome of the dissertation can assist programmers to understand and improve their programming skills.
In Chapter 2, a comprehensive data analysis framework is proposed to extract hidden features and association rules using a real-world dataset of an OJ system. Initially, an unsupervised modified K-means (MK-means) clustering algorithm is applied for data clustering, and then the frequent pattern (FP)-growth algorithm is used for association rule mining. We leverage students' program submission logs and academic scores as an experimental dataset. To explore the correlation between programming skills and overall academic performance, the statistical features of students are analyzed and the related results are presented including hidden features, common errors made by students, submission trends, frequent patterns, association rules, and so on. A number of useful recommendations are provided for students in each cluster based on the identified hidden features. In addition, the analytical results of this Chapter can help teachers prepare effective lesson plans, evaluate programs with special arrangements, and identify the academic weaknesses of students. Furthermore, a prototype of the proposed approach and data-driven analytical results can be applied to other practical courses in ICT or engineering disciplines. Based on the data analysis, we identified most common errors made by programmers during their learning processes. We found that many of the errors encountered could not be evaluated or detected by conventional compilers. Moreover, it is difficult to assess and detect logic errors (e.g., time limit exceeded, run time error, memory limit exceeded, output limit exceeded, etc.) in the source code with traditional compilers, resulting in erroneous code.
In Chapter 3, we proposed a source code assessment and classification model. The proposed model is developed based on a long short-term memory (LSTM) neural network with an attention mechanism to assess and classify the source code. The attention mechanism enhances the accuracy of the proposed model for assessment and classification. Thus, the proposed model can detect source code errors with locations and then predict the correct word for error. In addition, the proposed model can classify the source codes whether it is erroneous or not. We trained the model using source codes and then evaluated the performance. The experimental results obtained show that the accuracy in terms of error detection and prediction of the proposed model approximately is 62% and source code classification (correct or incorrect) accuracy approximately is 96% that outperformed a standard LSTM and other state-of-the-art models. Overall, these experimental results indicate the usefulness of the proposed model in professional programming and programming education fields. Furthermore, the proposed model can help programmers to reduce errors in solution codes that cannot be detected by conventional compilers. Despite the good performance of LSTM-based model, it still has a shortcoming that it only considers the past context of the input sequences, but cannot consider any future (i.e., subsequent) context.
In Chapter 4, we proposed a sequential language model for evaluating source codes using a bidirectional long short-term memory (BiLSTM) neural network. The BiLSTM model can consider both the past and future context of the input sequences. We trained the BiLSTM model with a large number of real-world source codes with tuning various hyperparameters. We then used the model to evaluate incorrect code and assessed the model’s performance in three principal areas: source code error detection, suggestions for incorrect code repair, and erroneous code classification. Experimental results showed that the proposed BiLSTM model achieved significant correctness in identifying errors and providing suggestions. Moreover, the model achieved an F-score of approximately 97%, outperforming other state-of-the-art models such as recurrent neural networks (RNNs) and LSTM. Furthermore, programmers have recently improved their programming skills and can now write code in many different languages to solve problems. A lot of new code is being generated all over the world regularly. Since a programming problem can be solved in many different languages, it is quite difficult to identify the algorithm from the written source code. Therefore, a classification model is needed to help programmers identify the algorithms in source code written/developed in Multi-Programming Languages (MPLs). The classification model can help programmers learn better programming. However, source code multi-class classification models based on deep learning are still lacking in the field of programming education and software engineering. To address this gap, we also proposed a multilingual source code classification model using stacked BiLSTM. To accomplish this task, we collect a large number of source codes from the Aizu Online Judge (AOJ) system. The stacked BiLSTM model is trained, validated, and tested on the real-world dataset. Various hyperparameters are fine-tuned to improve the performance of the model. Based on the experimental results, the stacked BiLSTM model achieved an accuracy of about 93% and an F1-score of 89.24%. Moreover, the model outperforms the state-of-the-art models in terms of other evaluation matrices such as precision (90.12%) and recall (89.48%).
... Visualizing and tracking learning progress [5], [20], [26], [27]. Adaptation [12], [24], [26]. ...
... Visualizing and tracking learning progress [5], [20], [26], [27]. Adaptation [12], [24], [26]. Prediction [10], [21], [28]. ...
... The method used to visualize the level of engagement [20], students' progress [5], achievement and leaderboard data [26], analyze and understand the influence of visual indicators on using a platform [11], and visualize students' learning and gamification data on different dashboards [27]. It also gathered access data, badge analytics, learning objectives, the grade predictor to visualize progress [21]. ...
The growing adoption of learning analytics (LA) approaches and data mining (DM) techniques using educational gamification data sets is reflected in increased publications on this topic. However, with different gamified contexts and a variety of LA methods available, no comprehensive review summarized the obtained findings. Therefore, this research aims to identify studies' characteristics, objectives, and methods used in gamification learning analytics (GaLA) research. To identify these, this study comprehensively reviewed the literature of 24 studies selected from an initial pool of 221 search results. The findings show that GaLA methods can be categorized into: visualization, data mining, social network analysis (SNA), statistics, and correlations. In conclusion, GaLA is defined as a data-driven approach using various methods of data analysis and mining techniques in gamified contexts for collecting, analyzing, and reporting data to assess or enhance the gameful experience, understand student behaviour, and improve learning outcomes.
