Search Results (2,967)

In an era where fake news detection has become a pressing issue due to its profound impacts on public opinion, democracy, and social trust, accurately identifying and classifying false information is a critical challenge. In this study, the effectiveness is investigated of advanced machine learning models—convolutional neural networks (CNNs), bidirectional encoder representations from transformers (BERT), and generative pre-trained transformers (GPTs)—for robust fake news classification. Each model brings unique strengths to the task, from CNNs’ pattern recognition capabilities to BERT and GPTs’ contextual understanding in the embedding space. Our results demonstrate that the fine-tuned GPT-4 Omni models achieve 98.6% accuracy, significantly outperforming traditional models like CNNs, which achieved only 58.6%. Notably, the smaller GPT-4o mini model performed comparably to its larger counterpart, highlighting the cost-effectiveness of smaller models for specialized tasks. These findings emphasize the importance of fine-tuning large language models (LLMs) to optimize the performance for complex tasks such as fake news classifier development, where capturing subtle contextual relationships in text is crucial. However, challenges such as computational costs and suboptimal outcomes in zero-shot classification persist, particularly when distinguishing fake content from legitimate information. By highlighting the practical application of fine-tuned LLMs and exploring the potential of few-shot learning for fake news detection, this research provides valuable insights for news organizations seeking to implement scalable and accurate solutions. Ultimately, this work contributes to fostering transparency and integrity in journalism through innovative AI-driven methods for fake news classification and automated fake news classifier systems. Full article

Research expands the boundaries of a subject, economy, and civilization. Peer review is at the heart of research and is understandably an expensive process. This work, with human-in-the-loop, aims to support the research community in multiple ways. It predicts quality, and acceptance, and recommends reviewers. It helps the authors and editors to evaluate research work using machine learning models developed based on a dataset comprising 18,000+ research papers, some of which are from highly acclaimed, top conferences in Artificial Intelligence such as NeurIPS and ICLR, their reviews, aspect scores, and accept/reject decisions. Using machine learning algorithms such as Support Vector Machines, Deep Learning Recurrent Neural Network architectures such as LSTM, a wide variety of pre-trained word vectors using Word2Vec, GloVe, FastText, transformer architecture-based BERT, DistilBERT, Google’s Large Language Model (LLM), PaLM 2, and TF-IDF vectorizer, a comprehensive system is built. For the system to be readily usable and to facilitate future enhancements, a frontend, a Flask server in the cloud, and a NOSQL database at the backend are implemented, making it a complete system. The work is novel in using a unique blend of tools and techniques to address most aspects of building a system to support the peer review process. The experiments result in a 86% test accuracy on acceptance prediction using DistilBERT. Results from other models are comparable, with PaLM-based LLM embeddings achieving 84% accuracy. Full article

Large language models (LLMs) have emerged as powerful tools for natural language processing tasks, revolutionizing the field with their ability to understand and generate human-like text. As the demand for more sophisticated LLMs continues to grow, there is a pressing need to address the computational challenges associated with their scale and complexity. This paper presents a comprehensive survey of hardware accelerators designed to enhance the performance and energy efficiency of large language models. By examining a diverse range of accelerators, including GPUs, FPGAs, and custom-designed architectures, we explore the landscape of hardware solutions tailored to meet the unique computational demands of LLMs. The survey encompasses an in-depth analysis of architecture, performance metrics, and energy efficiency considerations, providing valuable insights for researchers, engineers, and decision-makers aiming to optimize the deployment of LLMs in real-world applications. Full article

This paper presents a novel neural network model for the detection of Structured Query Language (SQL) injection attacks for web applications. The model features high detection accuracy, fast inference speed, and low weight size. The model is based on a novel Natural Language Processing (NLP) technique, where a tokenizer for converting SQL queries into tokens is adopted as a pre-processing stage for detection. Only SQL keywords and symbols are considered as tokens for removing noisy information from input queries. Moreover, semantic labels are assigned to tokens for highlighting malicious intentions. For the exploration of correlation among the tokens, a lightweight multi-head self-attention scheme with a position encoder is employed. Experimental results show that the proposed algorithm has high detection performance for SQL injection. In addition, compared to its lightweight NLP counterparts based on self-attention, the proposed algorithm has the lowest weight size and highest inference speed. It consumes only limited computation and storage overhead for web services. In addition, it can even be deployed in the edge devices with low computation capacity for online detection. The proposed algorithm therefore is an effective low-cost solution for SQL injection detection. Full article

Aim: This review aims to explore the clinical applications, biological mechanisms, and potential benefits of concentrated growth factors (CGFs), autologous materials, and xenografts in bone regeneration, particularly in dental treatments such as alveolar ridge preservation, mandibular osteonecrosis, and peri-implantitis. Materials and Methods. A systematic literature search was conducted using databases like PubMed, Scopus, and Web of Science, with keywords such as “bone regeneration” and “CGF” from 2014 to 2024. Only English-language clinical studies involving human subjects were included. A total of 10 studies were selected for qualitative analysis. Data were processed through multiple stages, including title and abstract screening and full-text evaluation. Conclusion: The findings of the reviewed studies underscore the potential of the CGF in enhancing bone regeneration through stimulating cell proliferation, angiogenesis, and extracellular matrix mineralization. Autologous materials have also demonstrated promising results due to their biocompatibility and capacity for seamless integration with natural bone tissue. When combined with xenografts, these materials show synergistic effects in improving bone quantity and quality, which are crucial for dental implant success. Future research should focus on direct comparisons of different techniques, the optimization of protocols, and broader applications beyond dental medicine. The integration of CGFs and autologous materials into routine clinical practice represents a significant advancement in regenerative dental medicine, with the potential for improved patient outcomes and satisfaction. Full article

This research presents an innovative approach in text mining based on rough set theory. This study fundamentally utilizes the concept of symmetry from rough set theory to construct indiscernibility matrices and model uncertainties in data analysis, ensuring both methodological structure and solution processes remain symmetric. The effective management and analysis of large-scale textual data heavily relies on automated text classification technologies. In this context, term weighting plays a crucial role in determining classification performance. Particularly, supervised term weighting methods that utilize class information have emerged as the most effective approaches. However, the optimal representation of class–term relationships remains an area requiring further research. This study proposes the Rough Multivariate Weighting Scheme (RMWS) and presents its mathematical derivative, the Square Root Rough Multivariate Weighting Scheme (SRMWS). The RMWS model employs rough sets to identify information-carrying documents within the document–term–class space and adopts a computational methodology incorporating α, β, and γ coefficients. Moreover, the distribution of the term among classes is again effectively revealed. Comprehensive experimental studies were conducted on three different datasets featuring imbalanced-multiclass, balanced-multiclass, and imbalanced-binary class structures to evaluate the model’s effectiveness. The results show that RMWS and its derivative SRMWS methods outperform existing approaches by exhibiting superior performance on balanced and unbalanced datasets without being affected by class imbalance and number of classes. Furthermore, the SRMWS method is found to be the most effective for SVM and KNN classifiers, while the RMWS method achieves the best results for NB classifiers. These results show that the proposed methods significantly improve the text classification performance. Full article

Text-to-image models have demonstrated remarkable progress in generating visual content from textual descriptions. However, the presence of linguistic ambiguity in the text prompts poses a potential challenge to these models, possibly leading to undesired or inaccurate outputs. This work conducts a preliminary study and provides insights into how text-to-image diffusion models resolve linguistic ambiguity through a series of experiments. We investigate a set of prompts that exhibit different types of linguistic ambiguities with different models and the images they generate, focusing on how the models’ interpretations of linguistic ambiguity compare to those of humans. In addition, we present a curated dataset of ambiguous prompts and their corresponding images known as the Visual Linguistic Ambiguity Benchmark (V-LAB) dataset. Furthermore, we report a number of limitations and failure modes caused by linguistic ambiguity in text-to-image models and propose prompt engineering guidelines to minimize the impact of ambiguity. The findings of this exploratory study contribute to the ongoing improvement of text-to-image models and provide valuable insights for future advancements in the field. Full article

Event detection is a crucial task in natural language processing, and it plays a significant role in numerous applications, such as information retrieval, question answering, and situational awareness. Real-world tasks typically require robust models that can dynamically adapt to changing data distributions and seamlessly accommodate emerging event types while maintaining high accuracy and efficiency. However, existing methods often face catastrophic forgetting, a significant challenge where models lose previously acquired knowledge when learning new information. This phenomenon hinders models from balancing performance with adaptability, limiting their ability to generalize across dynamic data landscapes. This paper proposes a novel event detection framework, DASR, which aims to enhance the flexibility and diversity of event detection through joint learning and guidance that dynamically adapts to new events and extracts semantic relevance. Firstly, we utilize pre-trained language models (PLMs) trained on general corpora to obtain existing event and type information as global knowledge. Secondly, during prompt fine-tuning for specific tasks, we incorporate an incremental learning module to design incremental prompt templates for newly introduced event types and read out their representations within the PLM. Subsequently, we perform entity recognition and event trigger word detection to extract semantic relevance. In this case, a graph attention mechanism is introduced to enhance the long-distance dependencies within the text (modeled as message passing in the type graph). Additionally, feature fusion integrates entity and event trigger word information into a unified representation. Finally, we validate the effectiveness of the proposed framework through extensive experiments. The experimental results demonstrate that the proposed framework effectively mitigates catastrophic forgetting and significantly improves the accuracy and adaptability of event detection when dealing with evolving data distributions and newly introduced event types. Full article

Active learning has been a research area conducted across various domains for a long time, from traditional machine learning to the latest deep learning research. Particularly, obtaining high-quality labeled datasets for supervised learning requires human annotation, and an effective active learning strategy can greatly reduce annotation costs. In this study, we propose a new insight, CFP-AL (Combining model Features and Prediction for Active Learning), from the perspective of feature space by analyzing and diagnosing methods that have shown good performance in NLP (Natural Language Processing) sentence classification. According to our analysis, while previous active learning strategies that focus on finding data near the decision boundary to facilitate classifier tuning are effective, there are very few data points near the decision boundary. Therefore, a more detailed active learning strategy is needed beyond simply finding data near the decision boundary or data with high uncertainty. Based on this analysis, we propose CFP-AL, which considers the model’s feature space, and it demonstrated the best performance across six tasks and also outperformed others in three Out-Of-Domain (OOD) tasks. While suggesting that data sampling through CFP-AL is the most differential classification standard, it showed novelty in suggesting a method to overcome the anisotropy phenomenon of supervised models. Additionally, through various comparative experiments with basic methods, we analyzed which data are most beneficial or harmful for model training. Through our research, researchers will be able to expand into the area of considering features in active learning, which has been difficult so far. Full article

Emergency situation awareness during sudden natural disasters presents significant challenges. Traditional methods, characterized by low spatial and temporal resolution as well as coarse granularity, often fail to comprehensively capture disaster situations. However, social media platforms, as a vital source of social sensing, offer significant potential to supplement disaster situational awareness. This paper proposes an innovative framework for disaster situation awareness based on multimodal data from social media to identify social media content related to typhoon disasters. Integrating text and image data from social media facilitates near real-time monitoring of disasters from the public perspective. In this study, Typhoon Haikui (Strong Typhoon No. 11 of 2023) was chosen as a case study to validate the effectiveness of the proposed method. We employed the ERNIE natural language processing model to complement the Deeplab v3+ deep learning image semantic segmentation model for extracting disaster damage information from social media. A spatial visualization analysis of the disaster-affected areas was performed by categorizing the damage types. Additionally, the Geodetector was used to investigate spatial heterogeneity and its underlying factors. This approach allowed us to analyze the spatiotemporal patterns of disaster evolution, enabling rapid disaster damage assessment and facilitating emergency response efforts. The results show that the proposed method significantly enhances situational awareness by effectively identifying different types of damage information from social sensing data. Full article

The rapid expansion of big data has transformed research practices across disciplines, yet disparities exist in its adoption among U.S. institutions of higher education. This study examines trends in NSF-funded big data-driven research across research domains, institutional classifications, and directorates. Using a quantitative approach and natural language processing (NLP) techniques, we analyzed NSF awards from 2006 to 2022, focusing on seven NSF research areas: Biological Sciences, Computer and Information Science and Engineering, Engineering, Geosciences, Mathematical and Physical Sciences, Social, Behavioral and Economic Sciences, and STEM Education (formally known as Education and Human Resources). Findings indicate a significant increase in big data-related awards over time, with CISE (Computer and Information Science and Engineering) leading in funding. Machine learning and artificial intelligence are dominant themes across all institutions’ classifications. Results show that R1 and non-minority-serving institutions receive the majority of big data-driven research funding, though HBCUs have seen recent growth due to national diversity initiatives. Topic modeling reveals key subdomains such as cybersecurity and bioinformatics benefiting from big data, while areas like Biological Sciences and Social Sciences engage less with these methods. These findings suggest the need for broader support and funding to foster equitable adoption of big data methods across institutions and disciplines. Full article

Artificial intelligence (AI), particularly through machine learning (ML) and deep learning (DL) techniques such as convolutional neural networks (CNNs) and natural language processing (NLP), has shown remarkable promise in image analysis and clinical documentation in oral pathology. In order to explore the transformative potential of artificial intelligence (AI) in oral pathology, this review highlights key studies demonstrating current AI’s improvement in oral pathology, such as detecting oral diseases accurately and streamlining diagnostic processes. However, several limitations, such as data quality, generalizability, legal and ethical considerations, financial constraints, and the need for paradigm shifts in practice, are critically examined. Addressing these challenges through collaborative efforts, robust validation, and strategic integration can pave the way for AI to revolutionize oral pathology, ultimately improving patient outcomes and advancing the field. Full article

In this paper, we present the results of a study on the development of a system to support medical diagnoses based on voice-based medical interviews. The main objective is to develop a tool that improves the process of collecting information from patients, using natural language analysis to identify key diagnostic information. The system processes the collected data to create information vectors for a selected group of diseases, allowing for an initial assessment of possible disease entities. An analysis of data mining and selected machine learning methods was carried out to develop an effective diagnosis algorithm. The system is designed to optimise patient care by automating the initial phase of the medical interview, which can lead to a reduction in errors due to subjective assessments and reduce the workload on doctors. The solution presented in this paper is part of a broader research project to develop a Medical Interview system, and this paper is the first article in a series that describes the experiences and challenges of implementing this system. Further work is planned to develop the model into advanced medical decision support techniques and validate it in a clinical setting. Full article

Periodontics is a complex field characterized by a constantly growing body of research, which poses a challenge for researchers and stakeholders striving to stay abreast of the evolving literature. Traditional bibliometric surveys, while accurate, are labor-intensive and not scalable to meet the demands of such rapidly expanding domains. In this study, we employed BERTopic, a transformer-based topic modeling framework, to map the thematic landscape of periodontics research published in MEDLINE from 2009 to 2024. We identified 31 broad topics encompassing four major thematic axes—patient management, periomedicine, oral microbiology, and implant-related surgery—thereby illuminating core areas and their semantic relationships. Compared with a conventional Latent Dirichlet Allocation (LDA) approach, BERTopic yielded more contextually nuanced clusters and facilitated the isolation of distinct, smaller research niches. Although some documents remained unlabeled, potentially reflecting either semantic ambiguity or niche topics below the clustering threshold, our results underscore the flexibility, interpretability, and scalability of neural topic modeling in this domain. Future refinements—such as domain-specific embedding models and optimized granularity levels—could further enhance the precision and utility of this method, ultimately guiding researchers, educators, and policymakers in navigating the evolving landscape of periodontics. Full article

Large Language Models (LLMs) like BERT have gained significant prominence due to their remarkable performance in various natural language processing tasks. However, they come with substantial computational and memory costs. Additionally, they are essentially black-box models, being challenging to explain and interpret. In this article, Persistent BERT Compression and Explainability (PBCE) is proposed, a Green AI methodology to prune BERT models using persistent homology, aiming to measure the importance of each neuron by studying the topological characteristics of their outputs. As a result, PBCE can compress BERT significantly by reducing the number of parameters (47% of the original parameters for BERT Base, 42% for BERT Large). The proposed methodology has been evaluated on the standard GLUE Benchmark, comparing the results with state-of-the-art techniques achieving outstanding results. Consequently, PBCE can simplify the BERT model by providing explainability to its neurons and reducing the model’s size, making it more suitable for deployment on resource-constrained devices. Full article