Online-Journals.org (International Association of Online Engineering)
Not a member yet
9805 research outputs found
Sort by
Predictive Analytics in Mobile Education: Evaluating Logistic Regression, Random Forest, and Gradient Boosting for Course Completion Forecasting
Get PDFThis study aimed to compare the effectiveness of three predictive algorithms—logistic regression, random forest, and GBM—in predicting course completion using user engagement data from online learning platforms. By analyzing engagement metrics such as session duration, session frequency, and quiz scores, the study sought to identify the most effective model for forecasting course completion, providing insights into which aspects of student behavior were most predictive of success. Logistic regression emerged as the best overall performer, achieving the highest accuracy (52.13%) and F1-Score (56.17%), indicating its balanced approach to predicting course completion and non-completion. Random forest and gradient boosting machines (GBM) showed strengths in specific areas; random forest maintained a good balance between precision and recall, while GBM excelled in recall, identifying students likely to complete courses but with lower precision, leading to more false positives. The findings have practical implications for educational technology, particularly in designing personalized learning paths and targeted interventions to support at-risk students. The study also acknowledged limitations, including the dataset’s focus on engagement metrics without demographic context and the potential for model-specific biases. Future research should explore additional predictive features, larger datasets, and more advanced algorithms to enhance the robustness and applicability of predictive models in real-time educational settings
The Potential of Artificial Intelligence in Education: Supporting Educational Transformation for Learners and Educators
Get PDFThe advent of text-generating artificial intelligence (AI) started a new era in education, offering transformative possibilities for both learners and educators. This article explores the potential of AI in education, its constructive applications in classrooms, and the necessary changes that must occur in higher education institutions and schools to integrate AI into learning processes. The paper explores potential benefits, challenges, and the importance of teacher-student collaboration in an AI-enhanced educational landscape. To address this, the paper discusses a multi-method comparative study focusing on students’ and pupils’ attitudes and preferences toward text-generating AI in classrooms and lecture halls.1 The study was implemented in two university courses and high school classes. A particular interest lies in data showing similarities and differences between pupils’ and students’ experiences with and attitudes towards textgenerating AI. The study uses semi-qualitative and quantitative interviews through written feedback forms. It analyzes the experiences and attitudes closely and in detail, thus investigating how pupils and students use AI in educational contexts and how they reflect their experiences. The paper also discusses how the results can be constructively implemented to improve future options for integrating AI tools in the higher education and school sectors.
1 In the following, the term “pupils” always refers to pupils in grades 9, 10 and 11. The term“students” always refers to students at a university
Phishing Susceptibility Among Healthcare Workers: The Impact of Awareness, Email Type, and Location
Get PDFWhile attempts by malicious actors to compromise computer systems continue to increase, there have been limited success in educating corporate learners. Most corporations must rely upon firewalls, email filtering, and other tools to prevent compromises since their employees vary in prevention reliability. Recent studies have shown limited success of anti-phishing awareness corporate learning campaigns; however, these studies have mostly utilized students or individuals aware of their participation in an experiment. The current research utilized healthcare workers. Over the course of 18 months and three experiments, we evaluated if different anti-phishing awareness learning campaigns, simulated phishing email content, or the employee’s work location (remote vs. on-site) factored into their susceptibility to phishing. We found that those participants who received anti-phishing awareness interacted with the simulated phishing email less than those who didn’t receive training. Overall, an average of four percent of the workers in each experiment submitted their credentials on the fraudulent website. Our results suggest any type of anti-phishing training may provide optimal results, at least regarding anti-phishing training
Affective Learning in the Context of Remote Experimentation
Get PDFWe analyzed the remote experiment’s position on “affective learning” and found that it significantly influenced students’ attitudes toward the applications. It emphasizes autonomy in learning and the coagulation aspects of ad hoc learning groups based on cognitive criteria, avoiding the artificial criteria (beautiful, ugly, sympathetic, unfriendly) typical of group formation in the physical environment. A detailed analysis of the students’ emotional responses, according to Wlodkowski’s classification, is made. The paper points out that the affective effect of the R.E. is treated as a secondary element in curricula, all assessments being oriented towards “cognitive learning” because the affective components involved are part of the “internal state” of the student. Based on Dave’s (1979) psychomotor taxonomy, the importance of R.E. in blended learning has been presented, where the cognitive content of learning remains unchanged, and the affective effect of the R.E. adds to teaching the techniques and the social dimensions
Evaluating User Experience in Learning Applications among University Students in Nigeria Using UEQ
Get PDFThis study evaluates the user experience (UX) of learning applications among university students in Nigeria using the user experience questionnaire (UEQ). With the rapid shift toward digital and mobile learning platforms in higher education, understanding students’ perceptions of usability, engagement, and overall satisfaction has become crucial. The study surveyed 397 university students to assess six key UX dimensions: attractiveness, perspicuity, efficiency, dependability, stimulation, and novelty. The findings revealed that the learning management system (LMS) users have a positive experience with it and use it frequently. The novelty category, on the other hand, has the lowest moodle mean score. We posit that these results are acceptable since the student aims to access the LMS to learn. The findings provide valuable insights for educators, developers, and policymakers aiming to optimize e-learning applications for improved usability and engagement. This study contributes to the broader conversation on enhancing digital learning experiences in developing regions
Interactive Mobile Technology in Education: A Systematic Mapping and Bibliometric Analysis
Get PDFInteractive mobile technology (IMT) has become an important element in the transformation of modern education, bringing a more open, dynamic, and responsive approach to learning for learners in the digital age. This study aims to explore the impact of using IMT in various educational settings, ranging from primary to tertiary levels. Through bibliometric analysis combined with a systematic review of a number of articles taken from the Scopus database and published over the last five years (2019–2023). This study identified key findings related to the purpose and focus of using IMT in education. The results indicate that these technologies aim to enhance student motivation, engagement, learning quality, critical thinking skills, and creativity, while also improving the accessibility and flexibility of learning. The findings imply that IMT has great potential to bring about positive changes in education, creating a learning environment that is more open, dynamic, and responsive to students’ individual needs. By utilizing this technology effectively, education can deliver learning experiences that are more engaging, relevant, and adaptive to learners’ development. Therefore, it needs to be continuously supported and developed to provide maximum benefits for the learning process and the advancement of education
AI-Powered Teaching: Literature Review of ChatGPT’s Impact on University Educators
Get PDFThe conversational artificial intelligence (AI) model ChatGPT has drawn significant interest from educators, as it opens up opportunities for innovations and provides substantial potential for use by university instructors. Since there is a lack of certainty about the effective application of ChatGPT in university teaching, the research reviews the available scientific studies to address these questions. The systematically analysed data cover two years (30.11.2022–30.11.2024). Based on the tasks set, the research identifies the spheres of university educators’ activities in which ChatGPT offers educationally valuable assistance. The ChatGPT-assisted teaching activities are examined and analysed with special attention to the benefits and concerns that the application of ChatGPT may bring to university teaching. ChatGPT’s integration into mobile-supported learning settings, highlighting its role in enabling ubiquitous learning, real-time feedback, and adaptive teaching support, is scrutinised. The recommendations for coping with the perceived negative aspects of ChatGPT in university educators’ teaching are revealed and highlighted. The distinct role of ChatGPT as a supportive means in university teaching is supported
Distributed Fuzzy Logic Algorithm for Cyberattack Detection and Energy Efficiency in Wireless Sensor Networks
Get PDFWireless sensor networks (WSNs) are critical for applications like environmental monitoring and industrial automation but face challenges balancing cybersecurity and energy efficiency. Existing approaches, such as centralized intrusion detection systems (IDS) and machine learning (ML) models, suffer from high computational overhead, scalability issues, and an inability to adapt to dynamic threats. This paper proposes a distributed fuzzy logic algorithm (DFLA) that integrates cyberattack detection and energy optimization through a decentralized architecture. By employing fuzzy logic to handle uncertainty, Dempster-Shafer theory for decision fusion, and the Reptile Search Algorithm for parameter adjustment, DFLA uses dual-objective rules to dynamically evaluate metrics such as packet drop rate, residual energy, and signal strength deviation. Nodes autonomously compute an attack risk level (ARL) and adjust transmission using localized fuzzy inference systems (FIS), minimizing reliance on cluster heads. Validated on real-world datasets (WSN-DS, CIC-IDS2017) and testbeds (TinyOS), DFLA achieves 99.87% detection accuracy for Blackhole and Flooding attacks, outperforming E-LEACH and RSA-IT2FLS while reducing energy consumption by 48%. The distributed design ensures scalability with lower communication overhead than centralized systems
Gamified Mobile Learning: EFL Students’ Attitudes Toward Quizizz for Grammar Instruction
Get PDFThis study explores Vietnamese English as a Foreign Language (EFL) students’ attitudes toward the application of Quizizz as a mobile-assisted language learning (MALL) tool for grammar instruction. With the increasing integration of gamified platforms in language education, understanding students’ perceptions and engagement with such tools is essential. The study employs a quantitative research design, collecting data from 102 students enrolled in a general English course at a university in northern Vietnam. Using a questionnaire, students’ attitudes were examined across affective, behavioral, and cognitive dimensions, along with their level of satisfaction with Quizizz. The findings indicate that students generally hold highly positive attitudes toward Quizizz, with high mean scores in affective (M = 4.4828, SD = 0.70383), behavioral (M = 4.3652, SD = 0.60594), and cognitive (M = 4.5025, SD = 0.61690) dimensions, highlighting strong emotional engagement, motivation, and perceived usefulness. A significant positive correlation between attitudes and satisfaction (r = .861, p < .01) underscores the effectiveness of Quizizz in fostering an engaging learning experience. However, an analysis of gender differences revealed no statistically significant variations in attitudes, suggesting that both male and female students perceive the platform similarly. The study concludes that Quizizz is a valuable tool for grammar learning, reinforcing motivation, engagement, and satisfaction. Findings contribute to theoretical discussions on MALL and gamification, offering practical implications for EFL educators seeking to integrate technology effectively into grammar instruction
Reinventing Trust: Traditional Media Credibility and Audience Engagement in the Mobile-First Era
Get PDFThe media landscape has undergone significant transformation due to the rapid development of digital technology. This has seriously threatened the legitimacy of traditional media. Given the emergence of new media platforms, this study investigated the variables affecting public confidence in traditional media. Using the uses and gratifications theory, the study examined how media audiences perceived news credibility, content quality, and technological adaptation. In-depth interviews with media professionals and regular news audiences revealed important themes pertaining to trust, bias, content depth, and audience engagement. The study provides insights into the necessity of digital transformation tactics to preserve audience trust, as well as the importance of fact-checking, investigative journalism, and balanced reporting in preserving credibility. The study also suggests ways to strengthen the position of traditional media in the digital information ecosystem