Search Results (663)

Optimizing spaced repetition schedules is of great importance for enhancing long-term memory retention in both real-world applications, e.g., online learning platforms, and academic applications, e.g., cognitive science. Traditional methods tackle this problem by employing handcrafted rules while modern methods try to optimize scheduling using deep reinforcement learning (DRL). Existing DRL-based approaches model the problem by selecting the optimal next item to appear, which implies the learner can only learn one item in a day. However, the most essential point to enhancing long-term memory is to select the optimal interval to review. To this end, we present a novel approach to DRL to optimize spaced repetition scheduling. The contribution of our framework is three-fold. We first introduce a Transformer-based model to estimate the recall probability of a learning item accurately, which encodes the temporal dynamics of a learner’s learning trajectories. Second, we build a simulation environment based on our recall probability estimation model. Third, we utilize the Deep Q-Network (DQN) as the agent to learn the optimal review intervals for learning items and train the policy in a recurrent manner. Experimental results demonstrate that our framework achieves state-of-the-art performance against competing methods. Our method achieves an MAE (mean average error) score of $0.0274$ on a memory prediction task, which is $11\%$ lower than the second-best method. For spaced repetition scheduling, our method achieves mean recall probabilities of $0.92$, $0.942$, and $0.372$ in three different environments, the best performance in all scenarios. Full article

At present, the integration of technology into education has generated a significant change in the way students access knowledge and develop skills. The availability of digital tools and online platforms has democratised access to information, allowing students to learn from anywhere and at any time. This article focuses on how the combination of artificial intelligence digital tools, such as ChatGPT, with one-to-one tutoring affects the development of soft skills in higher education students. A total of 182 university students participated in the study, divided into two groups. One group was required to construct an academic topic autonomously using only ChatGPT. The other group used the ChatGPT tool in conjunction with personal tutoring, with the teacher present to expand knowledge and enrich learning. The findings suggest that a combination of technology and meaningful human interactions is necessary to optimise the educational experience. While digital tools can be beneficial in accessing knowledge and developing skills, it is essential to acknowledge the value of individual connections with teachers in fostering authentic and deep learning. Furthermore, the study considers the potential necessity to modify and refocus both teaching participation and the student assessment system. This would entail a shift away from an emphasis on the memorisation of theoretical knowledge and towards the training and development of soft skills, competences, values and social implications. Full article

This article examines the communication and marketing requirements of a prospective business enterprise that specializes in offering online courses focusing on psychology, personal growth and professional development to change patterns of educational production and consumption. The objective of this research is to analyse the necessary brand positioning for this company to improve its visibility, attracting and retaining interested customers. Using a sequential and evidence-based methodology, this study analyses the precise business requirements to establish an optimal and competitive platform for professionals offering wellbeing courses. This involved analysing the characteristics and needs of the target audience—the professionals who would deliver the courses—and the audience who would enrol in the courses. In addition, we assessed the company’s environmental context, its strengths, weaknesses and unique selling points, as well as effective marketing and positioning strategies, and its direct competitors. We identified a growing interest in online training of courses that contribute to wellbeing. Among the target audience, preferences were diverse, with 58.1% leaning towards personal growth, 45.9% interested in meditation and 43.2% in psychology. Social media, particularly YouTube (52.7%), served as the main source of information for these courses. Criticisms focused mainly on issues such as poor visual and audio quality (20%), inadequate structuring of content (30%) and perceived boredom (23.6%). Addressing these preferences through multilingual translation, niche targeting, diverse course offerings, flexible pricing and membership options can effectively cater to diverse customer segments. The findings emphasise the importance of prioritising audiovisual quality and personalised learning experiences to foster audience loyalty. Full article

Abstract: Online platforms shape and facilitate our social, economic, and political activities. Sex workers have long pioneered their use for advertising, providing services, screening clients, collecting payments, and peer-interaction, among other activities. To learn more about the platforms sex workers use and how they engage and resist platforms’ power, we consider the following questions: How and to what extent do sex workers engage with online platforms? How do these platforms’ policies and practices shape the conditions of their work? And, how do sex workers negotiate these platforms’ power? Drawing on data from a national survey of 440 sex workers, developed in partnership with sex workers across the United States, we found that sex workers use a range of online platforms for their work. However, platform policies and practices often remove and/or limit sex workers’ access, thereby restricting their ability to earn income and also compromising their safety, and these effects stratify along the lines of race, gender, and ability. Sex workers respond to and resist platforms’ policies through various pre-emptive and pro-active actions. Our study expands the existing research on sex work and online platforms, particularly to illuminate the consequences of corporate-led platform policy development and implementation for marginalized workers. Full article

This paper introduces the INFLUTRUST framework that is designed to address challenges in trust-based influencer marketing campaigns on Online Social Networks (OSNs). The INFLUTRUST framework enables the influencers to autonomously select products across the OSN platforms for advertisement by employing a reinforcement learning algorithm. The Stochastic Learning Automata reinforcement algorithm considers the OSN platforms’ provided monetary rewards, the influencers’ advertising profit, and the influencers’ trust levels towards the OSN platforms to enable the influencers to autonomously select an OSN platform. The trust model for the influencers incorporates direct and indirect trust, which are derived from past interactions and social ties among the influencers and the OSN platforms, respectively. The OSN platforms allocate rewards through a multilateral bargaining model that supports competition among the influencers. Simulation-based results validate the INFLUTRUST framework’s effectiveness across diverse scenarios, with the scalability analysis demonstrating its robustness. Comparative evaluations highlight the INFLUTRUST framework’s superiority in considering trust levels and reward allocation fairness, benefiting both the influencers and the OSN platforms. Full article

The ever-evolving landscape of digital health technology has dramatically enhanced patients’ ability to manage their health through self-care effectively. These advancements have created various categories of self-care products, including medication management, health tracking, and wellness. There is no published research regarding integrating digital health into pharmacy self-care courses. This study aims to identify pertinent digital health devices and applications to incorporate into self-care course education. Digital health limitations, challenges incorporating digital health in self-care pharmacy education, and potential solutions are also reviewed. In conducting this research, many resources, including PubMed, APhA, ASHP, fda.gov, and digital.health, were reviewed in March 2024 to gather information on digital health devices and applications. To supplement this, targeted keyword searches were conducted on topics such as “digital health”, “devices”, “applications”, “technology”, and “self-care” across various online platforms. We identified digital health devices and applications suitable for self-care education across eight topics, as follows: screening, insomnia, reproductive disorders, eye disorders, home medical equipment, GI disorders, pediatrics, and respiratory disorders. Among these topics, wellness screening had the most digital health products available. For all other topics, at least three or more products were identified as relevant to self-care curriculum. By equipping students with digital health knowledge, they can effectively apply it in patient care throughout their rotations and future practice. Many digital health products, including telemedicine, electronic health records, mobile health applications, and wearable devices, are ideal for inclusion in pharmacy curriculum as future educational material. Future research is needed to develop the best strategies for incorporating relevant digital health into self-care education and defining the best student-learning strategies. Full article

Social media platforms and online gaming sites play a pervasive role in facilitating peer interaction and social development for adolescents, but they also pose potential threats to health and safety. It is crucial to tackle cyberbullying issues within these platforms to ensure the healthy social development of adolescents. Cyberbullying has been linked to adverse mental health outcomes among adolescents, including anxiety, depression, academic underperformance, and an increased risk of suicide. While cyberbullying is a concern for all adolescents, those with disabilities are particularly susceptible and face a higher risk of being targets of cyberbullying. Our research addresses these challenges by introducing a personalized online virtual companion guided by artificial intelligence (AI). The web-based virtual companion’s interactions aim to assist adolescents in detecting cyberbullying. More specifically, an adolescent with ASD watches a cyberbullying scenario in a virtual environment, and the AI virtual companion then asks the adolescent if he/she detected cyberbullying. To inform the virtual companion in real time to know if the adolescent has learned about detecting cyberbullying, we have implemented fast and lightweight cyberbullying detection models employing the T5-small and MobileBERT networks. Our experimental results show that we obtain comparable results to the state-of-the-art methods despite having a compact architecture. Full article

Large-scale computer platforms that process users’ online requests must be capable of handling unexpected spikes in arrival rates. These platforms, which are composed of distributed components, can be configured with parameters to ensure both the quality of the results obtained for each request and low response times. In this work, we propose a dynamic optimization engine based on metric space indexing to address this problem. The engine is integrated into the platform and periodically monitors performance metrics to determine whether new configuration parameter values need to be computed. Our case study focuses on a P2P platform designed for classifying crowdsourced images related to natural disasters. We evaluate our approach under scenarios with high and low workloads, comparing it against alternative methods based on deep reinforcement learning. The results show that our approach reduces processing time by an average of 40%. Full article

High-altitude platform (HAP) drones and satellites collaborate to form a network that provides edge computing services to terrestrial internet of things (IoT) devices, which is considered a promising method. In this network, IoT devices’ tasks can be split into multiple parts and processed by servers at non-terrestrial nodes in different locations, thereby reducing task processing delays. However, splitting tasks and allocating communication and computing resources are important challenges. In this paper, we investigate the task offloading and resource allocation problem in multi-HAP drones and multi-satellite collaborative networks. In particular, we formulate a task splitting and communication and computing resource optimization problem to minimize the total delay of all IoT devices’ tasks. To solve this problem, we first transform and decompose the original problem into two subproblems. We design a task splitting optimization algorithm based on deep reinforcement learning, which can achieve online task offloading decision-making. This algorithm structurally designs the actor network to ensure that output actions are always valid. Furthermore, we utilize convex optimization methods to optimize the resource allocation subproblem. The simulation results show that our algorithm can effectively converge and significantly reduce the total task processing delay when compared with other baseline algorithms. Full article

The Ebola virus disease (EVD) is an extremely contagious and fatal illness caused by the Ebola virus. Recently, Uganda witnessed an outbreak of EVD, which generated much attention on various social media platforms. To ensure effective communication and implementation of targeted health interventions, it is crucial for stakeholders to comprehend the sentiments expressed in the posts and discussions on these online platforms. In this study, we used deep learning techniques to analyse the sentiments expressed in Ebola-related tweets during the outbreak. We explored the application of three deep learning techniques to classify the sentiments in 8395 tweets as positive, neutral, or negative. The techniques examined included a 6-layer convolutional neural network (CNN), a 6-layer long short-term memory model (LSTM), and an 8-layer Bidirectional Encoder Representations from Transformers (BERT) model. The study found that the BERT model outperformed both the CNN and LSTM-based models across all the evaluation metrics, achieving a remarkable classification accuracy of 95%. These findings confirm the reported effectiveness of Transformer-based architectures in tasks related to natural language processing, such as sentiment analysis. Full article

MOOCs, the Massive Open Online Courses, are online educational courses that offer open access to a large number of participants globally. However, online engagement during MOOC learning remains a problem, as reflected in relatively high dropout rates. This paper involves academic and emotional support, aiming to explore whether they contribute to users’ sustainable use of the MOOC platform. A total of 410 college students learning English as a foreign language (EFL) and with MOOC learning experience participated in this study. Employing the structural equation modeling (SEM) techniques, we examined the relationships among five factors in the EFL MOOC learning context: academic support (AS), emotional support (ES), perceived usefulness (PU), perceived ease of use (PEoU), and platform reputation (PR). The results indicate that academic support influences learners’ perceptions of the usefulness and ease of use of the MOOC platform, as well as enhancing learners’ feelings of being emotionally supported. Simultaneously, platform reputation plays a crucial role in influencing learners’ perceptions of MOOC platforms. However, results suggest that emotional support does not have a statistically significant impact on the perceived usefulness and perceived ease of use of the platform in EFL MOOC learning contexts. Full article

Monitoring and evaluation of soil ecological environments are very important to ensure saline–alkali soil health and the safety of agricultural products. It is of foremost importance to, within a regional ecological risk-reduction strategy, develop a useful online system for soil ecological assessment and prediction to prevent people from suffering the threat of sudden disasters. However, the traditional manual or empirical parameter adjustment causes the mismatch of the hyperparameters of the model, which cannot meet the urgent need for high-performance prediction of soil properties using multi-dimensional data in the WebGIS system. To this end, this study aims to develop a saline–alkali soil ecological monitoring system for real-time monitoring of soil ecology in the Yellow River Delta, China. The system applied advanced web-based GIS, including front-end and back-end technology stack, cross-platform deployment of machine learning models, and a database embedded in multi-source environmental variables. The system adopts a five-layer architecture and integrates functions such as data statistical analysis, soil health assessment, soil salt prediction, and data management. The system visually displays the statistical results of air quality, vegetation index, and soil properties in the study area. It provides users with ecological risk assessment functions to analyze heavy metal pollution in the soil. Specially, the system introduces a tree-structured Parzan estimator (TPE)-optimized machine learning model to achieve accurate prediction of soil salinity. The TPE–RF model had the highest prediction accuracy (R² = 94.48%) in the testing set in comparison with the TPE–GBDT model, which exhibited a strong nonlinear relationship between environmental variables and soil salinity. The system developed in this study can provide accurate saline–alkali soil information and health assessment results for government agencies and farmers, which is of great significance for agricultural production and saline–alkali soil ecological protection. Full article

Human trafficking thrives in the shadows, and the rise of social media has provided traffickers with a powerful and unregulated tool. This paper delves into how these criminals exploit online platforms to target and manipulate vulnerable populations. A thematic analysis of existing research explores the tactics used by traffickers on social media, revealing how algorithms can be manipulated to facilitate exploitation. Furthermore, the paper examines the limitations of current regulations in tackling this online threat. The research underscores the urgent need for collaboration between governments and researchers to combat algorithmic exploitation. By harnessing data analysis and machine learning, proactive strategies can be developed to disrupt trafficking networks and protect those most at risk. Full article

Students’ engagement is a fundamental challenge in large classrooms in higher education. In recent years, innovative technologies such as electronic learning and online polling platforms have made learning more engaging, effective, and interactive. By using these platforms, educators can create more inclusive and enriching learning environments. This paper presents a novel approach in which an online technology is employed to enhance students’ learning experience. In this approach, features of an online polling platform, i.e., Slido, are employed to enhance students’ engagement in an engineering module, i.e., ‘Mechanics of Solids’, which is recognised as a fundamentally challenging module with difficult subjects. This study investigates how the interactive features of such technologies, such as real-time polls, question and answer (Q&A) sessions, and quizzes, can provide a more active and practical learning environment by improving student engagement in the classroom. In total, six online polls were designed: one for ice-breaking, two on the topics of shear forces and bending moment, two on stresses, and one on deflection. Each poll was presented to the students, and they participated in them by scanning a QR code or typing the poll’s code online. The rate of students’ participation in polls is extensively discussed to show the effectiveness of the proposed method. The findings of this study show a significant increase in student participation in classroom activities compared to traditional methods. Student feedback also indicates a positive learning experience with the use of the proposed approach. It is shown that the proposed approach has the potential to transform the way engineering students engage with challenging subjects, leading to enhanced learning outcomes and a more positive learning experience. Full article

With the popularity of mobile networks and intelligent terminals, online fragmented learning, as a new learning method, has become the mainstream way for college students to acquire knowledge and study independently. However, college students are prone to “accept-interruption” in online fragmented learning; thus, it is difficult for them to master a complete knowledge system and form a rigorous logic system, which is essential to ensure the effect of online fragmented learning. Therefore, this study investigates the antecedents of college students’ continuance behaviors in online fragmented learning (CBOFL). Based on the expectation confirmation model (ECM), a theoretical model is developed to examine the factors influencing college students’ CBOFL. Taking a total of 429 undergraduate students who have studied contest courses on the Chinese university massive open online courses (MOOCs) for research subjects, the mechanism underlying the determinants of college students’ CBOFL is analyzed, and six hypotheses are tested by a structural equation modeling (SEM) technique with AMOS. The results indicate that confirmation positively impacts intrinsic learning motivation and satisfaction; intrinsic learning motivation, satisfaction, and teachers’ influence all significantly positively affect college students’ CBOFL. Additionally, the predicting powers of different factors on college students’ CBOFL vary broadly; therein, satisfaction has the most significant effect. This study makes theoretical contributions to the quantitative research on college students’ CBOFL and literature on the ECM. Still, it also has important practical significance in guiding college students’ CBOFL and facilitating the sustainability of online fragmented learning. Full article