Search Results (369)

In this post-digital age, writing assessment has been markedly influenced by advancements in artificial intelligence (AI), emphasizing the role of automated formative feedback in supporting second language (L2) writing. This study investigates how Norwegian teachers use an AI-driven automated feedback tool, the Essay Assessment Technology (EAT), in process writing for the first time. Framed by the second and third-order barriers framework, we looked at teachers’ beliefs and the design level changes that they made in their teaching. Data were collected in Autumn 2022, during the testing of EAT’s first prototype. Teachers were first introduced to EAT in a workshop. A total of 3 English as a second language teachers from different schools were informants in this study. Teachers then used EAT in the classroom with their 9th-grade students (13 years old). Through individual teacher interviews, this descriptive qualitative study explores teachers’ perceptions, user experiences, and pedagogical decisions when incorporating EAT into their practices. The findings indicate that teachers’ beliefs about technology and its role in student learning, as well as their views on students’ responsibilities in task completion, significantly influence their instructional choices. Additionally, teachers not only adopt AI-driven tools but are also able to reflect and solve complex teaching and learning activities in the classroom, which demonstrates that these teachers have applied design thinking processes in integrating technology in their teaching. Based on the results in this study, we suggest the need for targeted professional development to support effective technology integration. Full article

The proliferation of hate speech on social media platforms poses significant threats to digital safety, social cohesion, and freedom of expression. Detecting such content—especially across diverse languages—remains a challenging task due to linguistic complexity, cultural context, and resource limitations. To address these challenges, this study introduces a comprehensive approach for multilingual hate speech detection. To facilitate robust hate speech detection across diverse languages, this study makes several key contributions. First, we created a novel trilingual hate speech dataset consisting of 10,193 manually annotated tweets in English, Spanish, and Urdu. Second, we applied two innovative techniques—joint multilingual and translation-based approaches—for cross-lingual hate speech detection that have not been previously explored for these languages. Third, we developed detailed hate speech annotation guidelines tailored specifically to all three languages to ensure consistent and high-quality labeling. Finally, we conducted 41 experiments employing machine learning models with TF–IDF features, deep learning models utilizing FastText and GloVe embeddings, and transformer-based models leveraging advanced contextual embeddings to comprehensively evaluate our approach. Additionally, we employed a large language model with advanced contextual embeddings to identify the best solution for the hate speech detection task. The experimental results showed that our GPT-3.5-turbo model significantly outperforms strong baselines, achieving up to an 8% improvement over XLM-R in Urdu hate speech detection and an average gain of 4% across all three languages. This research not only contributes a high-quality multilingual dataset but also offers a scalable and inclusive framework for hate speech detection in underrepresented languages. Full article

Inclusive music education refers to the use of musical experiences and practices as tools for promoting participation, equity, and meaningful engagement among all learners, including those with Special Educational Needs (SEN). Music education has long been recognized not only for its value in emotional expression and cultural transmission but also for its cognitive and relational benefits. This entry examines the inclusive and transformative potential of music, highlighting how it can foster equitable, accessible, and culturally relevant learning environments. Drawing from pedagogy, neuroscience, and educational technology, the entry explores how music contributes to cognitive, emotional, and social development, with a focus on learners with SEN. It emphasizes the importance of early exposure to music, the strong connections between music and language acquisition, and the need to challenge persistent misconceptions about innate musical talent. The findings demonstrate that when supported by digital tools and educational games, music education becomes a powerful driver of inclusion, enhancing participation, relational dynamics, and cognitive engagement. The entry concludes by advocating for a reimagining of music not as a secondary subject, but as a foundational component of holistic and inclusive education, capable of building more empathetic, connected, and equitable societies. Full article

The Amazigh language, spoken by millions across North Africa, presents unique computational challenges due to its complex morphological system, dialectal variation, and multiple writing systems. This survey examines technological advances over the past decade across four key domains: natural language processing, speech recognition, optical character recognition, and machine translation. We analyze the evolution from rule-based systems to advanced neural models, demonstrating how researchers have addressed resource constraints through innovative approaches that blend linguistic knowledge with machine learning. Our analysis reveals uneven progress across domains, with optical character recognition reaching high maturity levels while machine translation remains constrained by limited parallel data. Beyond technical metrics, we explore applications in education, cultural preservation, and digital accessibility, showing how these technologies enable Amazigh speakers to participate in the digital age. This work illustrates that advancing language technology for marginalized languages requires fundamentally different approaches that respect linguistic diversity while ensuring digital equity. Full article

The integration of digital serious games into speech learning (rehabilitation) has demonstrated significant potential in enhancing accessibility and inclusivity for children with speech disabilities. This review of the state of the art examines the role of serious games, Artificial Intelligence (AI), and Natural Language Processing (NLP) in speech rehabilitation, with a particular focus on interaction modalities, engagement autonomy, and motivation. We have reviewed 45 selected studies. Our key findings show how intelligent tutoring systems, adaptive voice-based interfaces, and gamified speech interventions can empower children to engage in self-directed speech learning, reducing dependence on therapists and caregivers. The diversity of interaction modalities, including speech recognition, phoneme-based exercises, and multimodal feedback, demonstrates how AI and Assistive Technology (AT) can personalise learning experiences to accommodate diverse needs. Furthermore, the incorporation of gamification strategies, such as reward systems and adaptive difficulty levels, has been shown to enhance children’s motivation and long-term participation in speech rehabilitation. The gaps identified show that despite advancements, challenges remain in achieving universal accessibility, particularly regarding speech recognition accuracy, multilingual support, and accessibility for users with multiple disabilities. This review advocates for interdisciplinary collaboration across educational technology, special education, cognitive science, and human–computer interaction (HCI). Our work contributes to the ongoing discourse on lifelong inclusive education, reinforcing the potential of AI-driven serious games as transformative tools for bridging learning gaps and promoting speech rehabilitation beyond clinical environments. Full article

The digital transformation of the Architecture, Engineering and Construction sector is accelerating the adoption of digital platforms as critical enablers of data integration, stakeholder collaboration and process optimization. This paper presents a systematic review of 125 peer-reviewed journal articles (2015–2025), selected through a PRISMA-guided search using the Scopus database, with inclusion criteria focused on English-language academic literature on platform-enabled digitalization in the built environment. Studies were grouped into six thematic domains, i.e., artificial intelligence in construction, digital twin integration, lifecycle cost management, BIM-GIS for underground utilities, energy systems and public administration, based on a combination of literature precedent and domain relevance. Unlike existing reviews focused on single technologies or sectors, this work offers a cross-sectoral synthesis, highlighting shared challenges and opportunities across disciplines and lifecycle stages. It identifies the functional roles, enabling technologies and systemic barriers affecting digital platform adoption, such as fragmented data sources, limited interoperability between systems and siloed organizational processes. These barriers hinder the development of integrated and adaptive digital ecosystems capable of supporting real-time decision-making, participatory planning and sustainable infrastructure management. The study advocates for modular, human-centered platforms underpinned by standardized ontologies, explainable AI and participatory governance models. It also highlights the importance of emerging technologies, including large language models and federated learning, as well as context-specific platform strategies, especially for applications in the Global South. Full article

Programming education has become increasingly vital within global K–12 curricula, and large language models (LLMs) offer promising solutions to systemic challenges such as limited teacher expertise and insufficient personalized support. Adopting a human-centric and systems-oriented perspective, this study employed a six-week quasi-experimental design involving 103 Grade 7 students in China to investigate the effects of instruction supported by the iFLYTEK Spark model. Results showed that the experimental group significantly outperformed the control group in programming performance, cognitive interest, and programming self-efficacy. Beyond these quantitative outcomes, qualitative interviews revealed that LLM-assisted instruction enhanced students’ self-directed learning, a sense of real-time human–machine interaction, and exploratory learning behaviors, forming an intelligent human–AI learning system. These findings underscore the integrative potential of LLMs to support competence, autonomy, and engagement within digital learning systems. This study concludes by discussing the implications for intelligent educational system design and directions for future socio-technical research. Full article

Background: Artificial intelligence and machine learning are playing crucial roles in digital transformation, aiming to improve the efficiency, effectiveness, equity, and responsiveness of primary health systems and their services. Method: Using synthetic knowledge synthesis and bibliometric and thematic analysis triangulation, we identified the most productive and prolific countries, institutions, funding sponsors, source titles, publications productivity trends, and principal research categories and themes. Results: The United States and the United Kingdom were the most productive countries; Plos One and BJM Open were the most prolific journals; and the National Institutes of Health, USA, and the National Natural Science Foundation of China were the most productive funding sponsors. The publication productivity trend is positive and exponential. The main themes are related to natural language processing in clinical decision-making, primary health care optimization focusing on early diagnosis and screening, improving health-based social determinants, and using chatbots to optimize communications with patients and between health professionals. Conclusions: The use of machine learning in primary health care aims to address the significant global burden of so-called “missed diagnostic opportunities” while minimizing possible adverse effects on patients. Full article

The current study examines the determinants influencing preparatory year (PY) students’ intentions to adopt AI-powered natural language processing (NLP) models, such as Copilot, ChatGPT, and Gemini, and how these intentions shape their conceptions of digital sustainability. Additionally, the extended unified theory of acceptance and use of technology (UTAUT) was integrated with a diversity of educational constructs, including content availability (CA), learning engagement (LE), learning motivation (LM), learner involvement (LI), and AI satisfaction (AS). Furthermore, responses of 274 PY students from Saudi Universities were analysed using partial least squares structural equation modelling (PLS-SEM) to evaluate both the measurement and structural models. Likewise, the findings indicated CA (β = 0.25), LE (β = 0.22), LM (β = 0.20), and LI (β = 0.18) significantly predicted user intention (UI), explaining 52.2% of its variance (R² = 0.522). In turn, UI significantly predicted students’ digital sustainability conceptions (DSC) (β = 0.35, R² = 0.451). However, AI satisfaction (AS) did not exhibit a moderating effect, suggesting uniformly high satisfaction levels among students. Hence, the study concluded that AI-powered NLP models are being adopted as learning assistant technologies and are also essential catalysts in promoting sustainable digital conceptions. Similarly, this study contributes both theoretically and practically by conceptualising digital sustainability as a learner-driven construct and linking educational technology adoption to its advancement. This aligns with global frameworks such as Sustainable Development Goals (SDGs) 4 and 9. The study highlights AI’s transformative potential in higher education by examining how user intention (UI) influences digital sustainability conceptions (DSC) among preparatory year students in Saudi Arabia. Given the demographic focus of the study, further research is recommended, particularly longitudinal studies, to track changes over time across diverse genders, academic specialisations, and cultural contexts. Full article

Traditional industrial robot programming methods often pose high usage thresholds due to their inherent complexity and lack of standardization. Manufacturers typically employ proprietary programming languages or user interfaces, resulting in steep learning curves and limited interoperability. Moreover, conventional systems generally lack capabilities for remote control and real-time status monitoring. In this study, a novel approach is proposed by integrating digital twin technology with traditional robot control methodologies to establish a virtual–real mapping architecture. A high-precision and efficient digital twin-based control platform for industrial robots is developed using the Unity3D (2022.3.53f1c1) engine, offering enhanced visualization, interaction, and system adaptability. The high-precision twin environment is constructed from the three dimensions of the physical layer, digital layer, and information fusion layer. The system adopts the socket communication mechanism based on TCP/IP protocol to realize the real-time acquisition of robot state information and the synchronous issuance of control commands, and constructs the virtual–real bidirectional mapping mechanism. The Unity3D platform is integrated to develop a visual human–computer interaction interface, and the user-oriented graphical interface and modular command system effectively reduce the threshold of robot use. A spatially curved part welding experiment is carried out to verify the adaptability and control accuracy of the system in complex trajectory tracking and flexible welding tasks, and the experimental results show that the system has high accuracy as well as good interactivity and stability. Full article

In the era of digital healthcare, electronic health records generate vast amounts of data, much of which is unstructured, and therefore, not in a usable format for conventional machine learning and artificial intelligence applications. This study investigates how to extract meaningful insights from unstructured radiology reports written in Finnish, a minority language, using machine learning techniques for text analysis. With this approach, unstructured information could be transformed into a structured format. The results of this research show that relevant information can be effectively extracted from Finnish medical reports using classification algorithms with default parameter values. For the detection of breast tumour mentions from medical texts, classifiers achieved high accuracy, almost 90%. Detection of metastasis mentions, however, proved more challenging, with the best-performing models Support Vector Machine (SVM) and logistic regression achieving an F1-score of 81%. The lower performance in metastasis detection is likely due to the more complex problem, ambiguous labeling, and the smaller dataset size. The results of classical classifiers were also compared with FinBERT, a domain-adapted Finnish BERT model. However, classical classifiers outperformed FinBERT. This highlights the challenge of medical language processing when working with minority languages. Moreover, it was noted that parameter tuning based on translated English reports did not significantly improve the detection rates, likely due to linguistic differences between the datasets. This larger translated dataset used for tuning comes from a different clinical domain and employs noticeably simpler, less nuanced language than the Finnish breast cancer reports, which are written by native Finnish-speaking medical experts. This underscores the need for localised datasets and models, particularly for minority languages with unique grammatical structures. Full article

With the rapid development of digital technologies, data-driven methods have demonstrated commendable performance in the toxic text detection task. However, several challenges remain unresolved, including the inability to fully capture the nuanced semantic information embedded in text languages, the lack of robust mechanisms to handle the inherent uncertainty of text languages, and the utilization of static fusion strategies for multi-view information. To address these issues, this paper proposes a comprehensive and dynamic toxic text detection method. Specifically, we design a multi-view feature augmentation module by combining bidirectional long short-term memory and BERT as a dual-stream framework. This module captures a more holistic representation of semantic information by learning both local and global features of texts. Next, we introduce an entropy-oriented invariant learning module by minimizing the conditional entropy between view-specific representations to align consistent information, thereby enhancing the representation generalization. Meanwhile, we devise a trustworthy text recognition module by defining the Dirichlet function to model uncertainty estimation of text prediction. And then, we perform the evidence-based information fusion strategy to dynamically aggregate decision information between views with the help of the Dirichlet distribution. Through these components, the proposed method aims to overcome the limitations of traditional methods and provide a more accurate and reliable solution for toxic language detection. Finally, extensive experiments on the two real-world datasets show the effectiveness and superiority of the proposed method in comparison with seven methods. Full article

The detection of abusive language in Roman Urdu is important for secure digital interaction. This work investigates machine learning (ML), deep learning (DL), and transformer-based methods for detecting offensive language in Roman Urdu comments collected from YouTube news channels. Extracted features use TF-IDF and Count Vectorizer for unigrams, bigrams, and trigrams. Of all the ML models—Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Naïve Bayes (NB)—the best performance was achieved by the same SVM. DL models involved evaluating Bi-LSTM and CNN models, where the CNN model outperformed the others. Moreover, transformer variants such as LLaMA 2 and ModernBERT (MBERT) were instantiated and fine-tuned with LoRA (Low-Rank Adaptation) for better efficiency. LoRA has been tuned for large language models (LLMs), a family of advanced machine learning frameworks, based on the principle of making the process efficient with extremely low computational cost with better enhancement. According to the experimental results, LLaMA 2 with LoRA attained the highest F1-score of 96.58%, greatly exceeding the performance of other approaches. To elaborate, LoRA-optimized transformers perform well in capturing detailed subtleties of linguistic nuances, lending themselves well to Roman Urdu offensive language detection. The study compares the performance of conventional and contemporary NLP methods, highlighting the relevance of effective fine-tuning methods. Our findings pave the way for scalable and accurate automated moderation systems for online platforms supporting multiple languages. Full article

ChatGPT, a prominent large language model developed by OpenAI, has rapidly become embedded in digital infrastructures across various sectors. This narrative review examines its evolving role and societal implications in three key domains: healthcare, education, and the economy. Drawing on recent literature and examples, the review explores ChatGPT’s applications, limitations, and ethical challenges in each context. In healthcare, the model is used to support patient communication and mental health services, while raising concerns about misinformation and privacy. In education, it offers new forms of personalized learning and feedback, but also complicates assessment and equity. In the economy, ChatGPT augments business operations and knowledge work, yet introduces risks related to job displacement, data governance, and automation bias. The review synthesizes these developments to highlight how ChatGPT is driving digital transformation while generating new demands for oversight, regulation, and critical inquiry. It concludes by outlining priorities for future research and policy, emphasizing the need for interdisciplinary collaboration, transparency, and inclusive access as generative AI continues to evolve. Full article

Background: Chronic diseases significantly burden healthcare systems due to the need for long-term treatment. Early diagnosis is critical for effective management and minimizing risk. The current traditional diagnostic approaches face various challenges regarding efficiency and cost. Digitized healthcare demonstrates several opportunities for reducing human errors, increasing clinical outcomes, tracing data, etc. Artificial Intelligence (AI) has emerged as a transformative tool in healthcare. Subsequently, the evolution of Generative AI represents a new wave. Large Language Models (LLMs), such as ChatGPT, are promising tools for enhancing diagnostic processes, but their potential in this domain remains underexplored. Methods: This study represents the first systematic evaluation of ChatGPT’s performance in chronic disease prediction, specifically targeting heart disease and diabetes. This study compares the effectiveness of zero-shot, few-shot, and CoT reasoning with feature selection techniques and prompt formulations in disease prediction tasks. The two latest versions of GPT4 (GPT-4o and GPT-4o-mini) are tested. Then, the results are evaluated against the best models from the literature. Results: The results indicate that GPT-4o significantly beat GPT-4o-mini in all scenarios regarding accuracy, precision, and F1-score. Moreover, a 5-shot learning strategy demonstrates superior performance to zero-shot, few-shot (3-shot and 10-shot), and various CoT reasoning strategies. The 5-shot learning strategy with GPT-4o achieved an accuracy of 77.07% in diabetes prediction using the Pima Indian Diabetes Dataset, 75.85% using the Frankfurt Hospital Diabetes Dataset, and 83.65% in heart disease prediction. Subsequently, refining prompt formulations resulted in notable improvements, particularly for the heart dataset (5% performance increase using GPT-4o), emphasizing the importance of prompt engineering. Conclusions: Even though ChatGPT does not outperform traditional machine learning and deep learning models, the findings highlight its potential as a complementary tool in disease prediction. Additionally, this work provides value by setting a clear performance baseline for future work on these tasks Full article