7712 research outputs found
Sort by
The Impact of Network Effects on Online Music Listening Behaviors
No full textThe network effects (NEs) play a vital role in the success of online platforms, fostering user collaboration and interest exchange, thereby creating a positive feedback loop that influences user behaviors and contributes to a platform’s success. However, initial studies exploring the NEs phenomenon primarily focused on network size, predating the widespread adoption of online platforms, and thus providing little insight into the application of NEs in the online platform context. This study aims to develop a comprehensive understanding of NEs on an online music platform by examining the social dynamics, specifically focusing on the social network and social actions of users, to uncover NEs impacts on music listening behaviors. Employing partial least square structural equation modeling (PLS-SEM) and analyzing longitudinal data, we delve into users’ music listening behaviors, examining changes in the quantity, novelty, and variety of music consumption. The panel data was obtained from Last.fm users at two points in time (N = 1,708 users, including 113,158 nodes and 252,747 edges in time 1, and 122,495 nodes and 364,158 edges in time 2). The research findings represent a novel contribution to the study of NEs, moving beyond network size, and provide empirical evidence of the impact of NEs on users’ music listening behaviors. The insights presented in this paper are instrumental in understanding the role of NEs on online platforms and in predicting user behaviors across various digital media domains, such as music, movies, and games
SmartGrid AI: enhancing home energy management with blockchain and deep learning for renewable integration
No full textSmartGrid AI revolutionizes home energy management by combining blockchain technology, deep learning, and vehicle-to-home (V2H) technology. It uses neural network-based Q-learning algorithms refined by advanced data preprocessing techniques such as normalization, standardization, and missing value imputation. These preprocessing steps ensure high-quality, accurate data for appliance planning and efficient energy storage management. V2H technology enables efficient energy transfer between electric vehicles and homes, optimizing energy consumption and reducing waste. Blockchain technology is used to secure and verify transactions, ensuring that all data exchanges are transparent and reliable. Real-time data from photovoltaic systems is integrated to improve the accuracy of energy management decisions. Using data from a Tunisian weather database, SmartGrid AI enables a significant 23% reduction in monthly electricity costs compared to traditional methods such as integer linear programming. The system’s advanced capabilities are demonstrated by its robust AI models, comprehensive performance metrics, efficient simulation models, and seamless integration of renewable energy sources. SmartGrid AI provides a cutting-edge solution for efficient and cost-effective home energy management
Economic and Social Impacts of Generative Artificial Intelligence
No full textGenerative artificial intelligence is transforming industries by enhancing efficiency in government services and reshaping sectors like agriculture, health care, manufacturing, and education. This special issue explores these transformations
Exploring AI Technology in Grammar Performance Testing for Children with Learning Disabilities
Full text linkThe study explores the application of artificial intelligence (AI) in addressing grammar challenges among children with learning disabilities, aiming to assess the efficacy of an AI-driven tool for personalized interventions. A sample of 100 children aged 8–12, diagnosed with learning disabilities, was recruited from special education programs. Participants were divided into an experimental group (n = 50), which used an AI-based grammar assessment tool with personalized feedback, and a control group (n = 50), which completed conventional paper-based grammar tests without feedback. The AI tool administered adaptive grammar tasks, including sentence correction and verb conjugation, and performance was evaluated over four weeks using pre-test and post-test measures. A quasi-experimental design and statistical analyses, including t-tests and repeated-measures ANOVA, revealed a significant improvement in grammar performance for the experimental group (M = 78.5, SD = 5.6) compared to the control group (M = 70.2, SD = 6.1; p \u3c 0.001), with a large effect size (Cohen’s d = 0.84). Participants and educators reported high engagement and usability of the tool. The findings underscore AI’s potential to provide tailored learning experiences, addressing individual needs more effectively than conventional strategies. Further research should examine long-term outcomes and broader educational applications to maximize its impact
Transforming education: Enhancing interactive learning through advanced prompt engineering techniques
No full textThis chapter delves into the transformative potential of prompt engineering for enhancing interactive learning by integrating advanced GenAI technologies. The strategic employment of prompt engineering offers a unique opportunity to customize and enrich learning environments. Educators can design engaging, adaptive, and personalized educational experiences by harnessing different AI tools. It examines how specific instructions and iterative processes involved in prompt engineering optimize AI-generated outputs and improve the quality of learning content. Through various case studies, from elementary to professional training, the effectiveness of tailored prompts in fostering deeper understanding, critical thinking, and creative problem-solving is highlighted. The challenges and ethical considerations are explored to ensure a balanced perspective on potential risks and rewards. This chapter guides stakeholders in utilizing prompt engineering to foster a more interactive, responsive, and inclusive learning landscape
Multimodal hate speech detection: a novel deep learning framework for multilingual text and images
No full textThe rapid proliferation of social media platforms has facilitated the expression of opinions but also enabled the spread of hate speech. Detecting multimodal hate speech in low-resource multilingual contexts poses significant challenges. This study presents a deep learning framework that integrates bidirectional long short-term memory (BiLSTM) and EfficientNetB1 to classify hate speech in Urdu-English tweets, leveraging both text and image modalities. We introduce multimodal multilingual hate speech (MMHS11K), a manually annotated dataset comprising 11,000 multimodal tweets. Using an early fusion strategy, text and image features were combined for classification. Experimental results demonstrate that the BiLSTM+EfficientNetB1 model outperforms unimodal and baseline multimodal approaches, achieving an F1-score of 81.2% for Urdu tweets and 75.5% for English tweets. This research addresses critical gaps in multilingual and multimodal hate speech detection, offering a foundation for future advancements
Innovative Neuropsychological Interventions for ADHD and Asperger\u27s Syndrome and Clinical Implications for Practitioners: Integrating Traditional Approaches With Emerging Technologies
No full textAttention-Deficit/Hyperactivity Disorder (ADHD) and Asperger’s Syndrome, which now falls under Autism Spectrum Disorder (ASD) according to the DSM- 5, represent two distinct yet sometimes overlapping neurodevelopmental disorders. Both conditions present significant cognitive, behavioral, and social challenges from early childhood through adolescence. As clinical understanding of these disorders has evolved, so too have the neuropsychological approaches to treatment. This chapter explores innovative intervention strategies that incorporate cutting- edge technology, evolving therapeutic practices, and a strengths- based approach to managing ADHD and Asperger’s Syndrome. By doing so, it offers a modern, comprehensive framework for treating these conditions in pediatric neuropsychology
Why Would I Befriend a Bot? Assessing Factors Influencing the Usage of Social Chatbots for Digital Natives
Full text linkWith advancements in artificial intelligence (AI), social chatbots (SCs) can now simulate meaningful, sympathetic interactions that blur the line between human and machine connection while also providing social and emotional support to its users. Generation Z (Gen Z), as tech-savvy digital natives, prefers individualized and emotionally engaging digital interactions, making them an important demographic for the adoption of AI-powered SCs. This study investigates the factors influencing Gen Z\u27s use of SCs, focusing on emotional support, attitudes towards AI, loneliness, and hedonic motivation. The study employed a quantitative survey with 156 participants who interacted with an SC and completed a questionnaire assessing key behavioral constructs. The findings reveal that emotional support and hedonic motivation significantly enhance trust in SCs, which in turn strongly predicts the intention to use them. To our surprise, loneliness had no measurable effect on the intention to use SCs, challenging assumptions that lonely individuals are more likely to adopt SCs. Privacy concerns similarly showed a negligible impact. These results highlight that fostering trust and providing enjoyable interactions are essential to promoting SC adoption among younger users
Optimizing fire detection in remote sensing imagery for edge devices: A quantization-enhanced hybrid deep learning model
Full text linkWildfires are increasing in frequency and severity, presenting critical challenges for timely detection and response, particularly in remote or resource-limited environments. This study introduces the Inception-ResNet Transformer with Quantization (IRTQ), a novel hybrid deep learning (DL) framework that integrates multi-scale feature extraction with global attention and advanced quantization. The proposed model is specifically optimized for edge deployment on platforms such as unmanned aerial vehicles (UAVs), offering a unique combination of high accuracy, low latency, and compact memory footprint. The IRTQ model achieves 98.9% accuracy across diverse datasets and shows strong generalization through cross-dataset validation. Quantization significantly reduces the parameter count to 0.09M and memory usage to 0.13 MB, enabling real-time inference in 3 ms. Interpretability is further enhanced through Grad-CAM visualizations, supporting transparent decision-making. While achieving state-of-the-art performance, the model encounters challenges in visually ambiguous fire-like regions. To address these, future work will explore multi-modal inputs and extend the model towards multi-class classification. IRTQ represents a technically grounded, interpretable, and deployable solution for AI-driven wildfire detection and disaster response
Examining the association between genetic polymorphisms and osteoporosis among post-menopausal women: a systematic review
Full text linkPurpose: Postmenopausal osteoporosis (PMOP) is the most prevalent metabolic bone disease among women, characterized by significant bone density loss and increased fracture risk. With a genetic component, a systematic review was conducted on the association between genetic polymorphisms and PMOP risk. Methods: A comprehensive review of PubMed literature examined genetic polymorphisms linked to PMOP risk. The primary outcome was to identify the most frequently studied genes linked to PMOP. The secondary outcome was to perform a meta-analysis on the top genetic markers to assess their overall association with PMOP risk. Results: Six genes, accounting for 55.08 % of all studies, were strongly associated with PMOP. Of these, the VDR gene was featured in 35 articles (18.72 % of studies), TNFRSF11B in 23 (12.30 %), ESR1 in 18 (9.63 %), COL1A1 in 12 (6.42 %), MTHFR in 8 (4.27 %), and TGFb1 in 7 (3.74 %). Meta-analysis showed five markers significantly associated with PMOP: SNP rs1544410 (ORG: 0.74 (0.59, 0.92)), SNP rs11568820 (ORG: 1.40 (1.03, 1.91)), and SNP rs2228570 (ORT: 1.39 (1.12, 1.73)) in the VDR gene; and PvuII variant (ORP: 0.80 (0.67, 0.96)) in the ESR1 gene. Conclusion: This review strengthens the importance of conducting a robust, multi-ethnic, large cohort study with functional analysis to corroborate the findings of the six key genes associated with PMOP. Replicating these findings in larger and more diverse datasets is crucial to validate their biological relevance and potential clinical application