Advanced Natural Language Research Articles

Cognitive Companion AI for Vulnerable Demographics: Fraud Prevention and Real-Time Protection for the Elderly

Online fraud is a growing threat, particularly for demographics such as the elderly, who are more susceptible to manipulative tactics and phishing attempts. This paper introduces "Cognitive Companion AI," a novel Agentic AI system designed to provide real-time fraud prevention and education for vulnerable users. Leveraging advanced natural language processing (NLP), emotion-aware analytics, contextual threat recognition, and human-in-the-loop monitoring, the Cognitive Companion analyzes online interactions for fraudulent indicators and provides live alerts with actionable explanations. The framework includes behavioral modeling and adaptive learning algorithms to stay ahead of evolving fraud tactics. The inclusion of human oversight enhances trust and ensures a failsafe mechanism for particularly high-risk scenarios, such as safeguarding elderly users. This system aims to empower users with protection and awareness, significantly reducing the risk of fraud while maintaining transparency and accessibility. This paper explores the framework, use cases, and human-in-the-loop mechanisms and addresses challenges in its implementation. Keywords Cognitive Companion AI, online fraud prevention, real-time threat detection, vulnerable demographics, natural language processing, explainable AI, human-in-the-loop systems, digital guardianship.

Evolving Strategies in Machine Learning: A Systematic Review of Concept Drift Detection

In this comprehensive literature review, we rigorously adhere to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for our process and reporting. This review employs an innovative method integrating the advanced natural language processing model T5 (Text-to-Text Transfer Transformer) to enhance the accuracy and efficiency of screening and data extraction processes. We assess strategies for handling the concept drift in machine learning using high-impact publications from notable databases that were made accessible via the IEEE and Science Direct APIs. The chronological analysis covering the past two decades provides a historical perspective on methodological advancements, recognizing their strengths and weaknesses through citation metrics and rankings. This review aims to trace the growth and evolution of concept drift mitigation strategies and to provide a valuable resource that guides future research and deepens our understanding of this rapidly changing field. Key findings highlight the effectiveness of diverse methodologies such as drift detection methods, window-based methods, unsupervised statistical methods, and neural network techniques. However, challenges remain, particularly with imbalanced data, computational efficiency, and the application of concept drift detection to non-tabular data like images. This review aims to trace the growth and evolution of concept drift mitigation strategies and provide a valuable resource that guides future research and deepens our understanding of this rapidly changing field.

Exploring research trends and patterns in leadership research: a machine learning, co-word, and network analysis

AbstractLeadership is recognized as playing a crucial role in the organization’s performance and success. As a result, the scientific literature on leadership has become quite extensive, making it difficult to identify and understand the current state of research. Most literature studies focus on a specific aspect of the field or a limited time frame, providing a fragmented view of the overall landscape. Therefore, this research aims to provide new insights into the current state of research through two studies. Using advanced Natural Language Processing (NLP) techniques, the first study focuses on identifying emerging research trends in the field through a Latent Dirichlet Allocation (LDA) model, providing insights into future areas of interest and investigation. The second study centers on analyzing consolidated research patterns through co-word and network analysis, shedding light on the connections and interrelationships between leadership research topics. By applying these techniques to a comprehensive dataset of 56,547 research papers gathered from Web of Science and Scopus, this study provides a detailed understanding of the current state of leadership research and identifies potential areas for future exploration. Five research trends were identified: (1) Leadership and Digital Transformation Research (LDTR); (2) Leadership and Organizational Performance Research (LOPR); (3) Educational Leadership Research (ELR); (4) Leadership Practices and Development Research (LPDR); and (5) Gender and Diversity Leadership Research (GDLR). Combining these five research trends with the consolidated research patterns identified, we propose several research directions identified for advancing leadership studies.

Cognitive Query System Using Generative AI

Abstract: The Cognitive Query System using Generative AI is a cutting-edge tool designed to transform the way we retrieve and analyse data from a wide range of sources, including text, images, and documents. Powered by the Google Gemini API and deployed through Streamlit, this system allows users to easily ask questions, process images, and explore document contents via an intuitive, interactive interface. The system comprises three core modules: the Question-Answering Module, which uses advanced natural language processing (NLP) techniques to provide contextually accurate, conversational responses to user queries, facilitating seamless, real-time interactions. The Image Processing and Querying Module enables users to upload images and ask questions related to their content, leveraging computer vision algorithms and AI to interpret and analyse visual data, making it easier to extract valuable insights. The Document Exploration Module supports various formats, including PDFs, Word documents, and spreadsheets, allowing users to quickly ask questions and navigate through sections without manual reading. Deployed online via Streamlit, the Cognitive Query System offers a smooth, real-time experience that does not require installation, making it ideal for remote and collaborative work environments. This innovative solution is designed to streamline workflows and effective outputs in the model.

Evaluating User Experience in E-Learning Platforms: An NLP-Enhanced Analysis of Duolingo Reviews

This study presents a novel framework to evaluate the usability and user experience of e-learning platforms, focusing on the Duolingo language learning app. By integrating advanced Natural Language Processing (NLP) techniques such as Large Language Models (LLMs), Latent Dirichlet Allocation (LDA), and sentence embedding models, we identified thirteen key usability and user experience topics from a large dataset of user reviews. Our findings reveal that Duolingo is highly rated since users value its enjoyable learning experiences and effectiveness. However, technical issues, lack of explanations, and frustrating features were identified as areas for improvement. The study demonstrates the effectiveness of our framework in analyzing user feedback at scale, offering valuable insights for improving user experience in e-learning platforms and other domains.

Keyphrase Identification Using Minimal Labeled Data with Hierarchical Contexts and Transfer Learning.

Interoperable clinical decision support system (CDSS) rules provide a pathway to interoperability, a well-recognized challenge in health information technology. Building an ontology facilitates creating interoperable CDSS rules, which can be achieved by identifying the keyphrases (KP) from the existing literature. Ontology construction is traditionally a manual effort by human domain experts, and the newly advanced natural language processing techniques, such as KP identification, can be a critical complementary automatic part of building ontology. However, KP identification requires human expertise, consensus, and contextual understanding for data labeling. This paper presents a semi-supervised KP identification framework (long short-term memory-based encoders and the conditional random fields -based decoder models, BiLSTM-CRF) using minimal human labeled data based on hierarchical attention (i.e., at word, sentence, and abstract levels) over the documents and domain adaptation. We created synthetic labels for initial training and human-labeled data for fine-tuning. We also tested different options during NLP preprocessing and ML training to optimize the ML pipeline. Our method outperforms the prior neural architectures by learning through synthetic labels for initial training, document-level contextual learning, language modeling, and fine-tuning with limited gold standard label data. After comparison, we found that the BIO encoding schema performed slightly better than Blue, and domain adaptation techniques can improve the quality of synthetic labels. In addition, document-level context, pre-trained LM, and pre-trained WE all contributed to better model performance in our tasks. Add 2 to 4 human-labeled documents for every 100 synthetic labeled documents improves the model performance without exhausting human-labeled documents too quickly. To the best of our knowledge, this is the first functional framework for the CDSS sub-domain to identify KPs, which is trained on limited human labeled data. It contributes to the general natural language processing (NLP) architectures in areas such as clinical NLP, where manual data labeling is challenging, and light-weighted deep learning models play an important role in real-time KP identification as a complementary approach to human experts' effort.

Differential Impacts of Environmental, Social, and Governance News Sentiment on Corporate Financial Performance in the Global Market: An Analysis of Dynamic Industries Using Advanced Natural Language Processing Models

This study examines how sentiment analysis of environmental, social, and governance (ESG) news affects the financial performance of companies in innovative sectors such as mobility, technology, and renewable energy. Using approximately 9828 general ESG articles from Google News and approximately 140,000 company-specific ESG articles, we performed term frequency-inverse document frequency (TF-IDF) analysis to identify key ESG-related terms and visualize their materiality across industries. We then applied models such as bidirectional encoder representations from transformers (BERT), the robustly optimized BERT pretraining approach (RoBERTa), and big bidirectional encoder representations from transformers (BigBird) for multiclass sentiment analysis, and distilled BERT (DistilBERT), a lite BERT (ALBERT), tiny BERT (TinyBERT), and efficiently learning an encoder that classifies token replacements accurately (ELECTRA) for positive and negative sentiment identification. Sentiment analysis results were correlated with profitability, cash flow, and stability indicators over a three-year period (2019–2021). ESG ratings from Morgan Stanley Capital International (MSCI), a prominent provider that evaluates companies’ sustainability practices, further enriched our analysis. The results suggest that sentiment impacts financial performance differently across industries; for example, positive sentiment correlates with financial success in mobility and renewable energy, while consumer goods often show positive sentiment even with low environmental ESG scores. The study highlights the need for industry-specific ESG strategies, especially in dynamic sectors, and suggests future research directions to improve the accuracy of ESG sentiment analysis.

Health Diagnostic Assistant using LLMs

The Health Diagnostic Assistant leverages advanced Large Language Models (LLMs) and Natural Language Processing (NLP) techniques to enhance patient diagnosis and healthcare decision-making. This innovative system employs Retrieval-Augmented Generation (RAG) to combine the strengths of pre-trained language models with a dynamic retrieval mechanism, allowing it to access and synthesize real-time medical knowledge from a wide array of databases. By analyzing patient symptoms, medical histories, and contextual data, the assistant generates accurate, context-aware recommendations and insights. The project aims to streamline the diagnostic process, reduce the burden on healthcare professionals, and improve patient outcomes by providing evidence-based suggestions tailored to individual cases. Through continuous learning and integration of user feedback, the Health Diagnostic Assistant aspires to evolve into a reliable tool for both patients and clinicians, fostering informed decision-making in the healthcare landscape.

Mitigating Bias in Large Language Models: A Multi-Task Training Approach Using BERT

Abstract. Large language models (LLMs), such as ChatGPT, have become essential tools due to their advanced natural language processing capabilities. However, these models, trained on extensive internet text, can inadvertently learn and propagate unwanted biases, impacting their outputs. This study addresses this issue by analyzing and mitigating such biases through a multi-task and multi-stage training approach. Utilizing the Winograd Bias (Winobias) dataset, the research fine-tunes the Bidirectional Encoder Representations from Transformers (BERT) model to reduce biased outputs. The approach includes an initial mask task to establish a general understanding and a subsequent cloze task to specifically target and mitigate biases. Results demonstrate a significant reduction in bias, with the original model showing approximately 90% certainty in biased outputs, whereas the de-biased model reduced this certainty to 55%. This study effectively showcases a method for bias reduction by modifying only a few parameters, emphasizing a practical approach to enhancing fairness and balance in LLMs used across various applications.

Performance of ChatGPT-3.5 and ChatGPT-4o in the Japanese National Dental Examination.

In this study, we compared the performance of ChatGPT-3.5 to that of ChatGPT-4o in the context of the Japanese National Dental Examination, which assesses clinical reasoning skills and dental knowledge, to determine their potential usefulness in dental education. ChatGPT's performance was assessed using 1399 (55% of the exam) of 2520 questions from the Japanese National Dental Examinations (111-117). The 1121 excluded questions (45% of the exam) contained figures or tables that ChatGPT could not recognize. The questions were categorized into 18 different subjects based on dental specialty. Statistical analysis was performed using SPSS software, with McNemar's test applied to assess differences in performance. A significant improvement was noted in the percentage of correct answers from ChatGPT-4o (84.63%) compared with those from ChatGPT-3.5 (45.46%), demonstrating enhanced reliability and subject knowledge. ChatGPT-4o consistently outperformed ChatGPT-3.5 across all dental subjects, with significant improvements in subjects such as oral surgery, pathology, pharmacology, and microbiology. Heatmap analysis revealed that ChatGPT-4o provided more stable and higher correct answer rates, especially for complex subjects. This study found that advanced natural language processing models, such as ChatGPT-4o, potentially have sufficiently advanced clinical reasoning skills and dental knowledge to function as a supplementary tool in dental education and exam preparation.

AI assistance in enterprise UX design workflows: enhancing design brief creation for designers.

The study explores the impact of AI tools on the daily tasks of designers in corporate environments, with a focus on the creation and evaluation processes of design briefs. Given ChatGPT's advanced natural language processing capabilities and its potential to meet the complex communication and analysis needs of design work, this tool was selected to investigate its application in designers' workflows. Through expert interviews, experimental testing, and third-party expert evaluations, we collected and analyzed data to understand the impact of AI on work processes. The findings indicate that AI tools significantly enhance both operational experience and subjective perceptions across most tasks. Additionally, the study provides a visual comparison of the testing process through a user experience map, highlighting AI's positive influence on work efficiency, information retrieval, verification, analysis, communication, and decision-making. However, challenges remain in ensuring information authenticity, protecting content copyright, and maintaining professional identity. The primary objective is to gain a comprehensive understanding of the current state of AI application in business contexts and its impact on designers' roles. By analyzing real-world feedback, the research aims to identify the strengths and weaknesses of AI solutions in enterprises and offer practical recommendations. The study underscores the importance of integrating AI thinking into workflows and adopting a human-centric approach for the future development of corporate work environments.

RISH Assistance: Voice Activated Digital Assistant for Developers

The increasing use of computing devices brings convenience but also challenges. Traditional interfaces can lead to repetitive strain, slow interactions, and accessibility problemsfor software developers, who often find it hard to turn complex ideas into code, especially with unfamiliar APIs. In response, there is a growing interest in automation and smart machines that act like humans. However, a major obstacle remains—the gap in human-machine interaction. Introducing “RISH Assistance,” a voice-activated digital assis- tant designed for developers. RISH enables users to navigate tasks more efficiently, reducing reliance on screens and tra- ditional input methods. Utilizing advanced voice recognition and Natural Language Processing (NLP), RISH transforms the developer experience by providing easy access to resources, seamless code suggestions, and natural troubleshooting—all through voice commands. Additionally, it can manage phone functions, allowing calls and messages directly from the desktop interface, enhancing productivity. Security is ensured with face authentication, and current session chat history tracking allowsusers to revisit previous interactions. RISH boosts productivity through hands-free interaction, en- abling developers to focus on creative problem-solving. It im- proves accessibility by offering an alternative input method and streamlines workflows, reducing cognitive load while fostering a more intuitive development environment. By facilitating natural and efficient engagement with machines, RISH Assistance aims to enhance human-machine collaboration and create a more inclusive software development landscape.

Compassionate Care with Autonomous AI Humanoid Robots in Future Healthcare Delivery: A Multisensory Simulation of Next-Generation Models.

The integration of AI and robotics in healthcare raises concerns, and additional issues regarding autonomous systems are anticipated. Effective communication is crucial for robots to be seen as "caring", necessitating advanced mechatronic design and natural language processing (NLP). This paper examines the potential of humanoid robots to autonomously replicate compassionate care. The study employs computational simulations using mathematical and agent-based modeling to analyze human-robot interactions (HRIs) surpassing Tetsuya Tanioka's TRETON. It incorporates stochastic elements (through neuromorphic computing) and quantum-inspired concepts (through the lens of Martha Rogers' theory), running simulations over 100 iterations to analyze complex behaviors. Multisensory simulations (visual and audio) demonstrate the significance of "dynamic communication", (relational) "entanglement", and (healthcare system and robot's function) "superpositioning" in HRIs. Quantum and neuromorphic computing may enable humanoid robots to empathetically respond to human emotions, based on Jean Watson's ten caritas processes for creating transpersonal states. Autonomous AI humanoid robots will redefine the norms of "caring". Establishing "pluralistic agreements" through open discussions among stakeholders worldwide is necessary to align innovations with the values of compassionate care within a "posthumanist" framework, where the compassionate care provided by Level 4 robots meets human expectations. Achieving compassionate care with autonomous AI humanoid robots involves translating nursing, communication, computer science, and engineering concepts into robotic care representations while considering ethical discourses through collaborative efforts. Nurses should lead the design and implementation of AI and robots guided by "technological knowing" in Rozzano Locsin's TCCN theory.

NIMG-63. LEVERAGING LLMS FOR ACCURATE DIFFERENTIATION OF RADIATION NECROSIS AND TUMOR PROGRESSION IN BRAIN MRI REPORTS: A STUDY ON AUTOMATED SCORING AND CLINICAL IMPLICATIONS

Abstract BACKGROUND Accurate differentiation between radiation necrosis and tumor progression or recurrence in patients treated with stereotactic radiosurgery for brain metastases is critical for guiding clinical management. This study leverages the advanced natural language processing capabilities of Meta Llama3, an artificial intelligence (AI) large language model (LLM), combined with prompt engineering, to rapidly categorize brain magnetic resonance imaging (MRI) radiology reports. Our objective was to develop an automated scoring system to classify concern for radiation necrosis, tumor progression, equivocal findings, or stable exams. METHODS Using a comprehensive dataset of reports annotated by expert radiologists, we ran inference on a 70-billion parameter Llama3 model (temperature 0.2, top_p 0.9) with specific prompts designed to capture the nuanced language and diagnostic criteria related to radiation necrosis or tumor progression. RESULTS The first pass was performed on a training dataset of 107 reports and did not predefine the clinical conditions. This demonstrated 43.4% accuracy in scoring when compared to a human user’s classification of each report. Agreement between the human reader and Llama3 was assessed using the Gwet agreement coefficient, AC1=0.411 (99%CI 0.396-0.426). Multiple iterations of targeted prompt engineering were then employed to narrow the definition of radiation necrosis and tumor progression, with specific examples and nuanced language used to achieve a higher degree of accuracy at 72.0%, AC1=0.719 (99%CI 0.717-0.722). DISCUSSION/FUTURE DIRECTIONS This surpasses recent demonstration of lower human-LLM agreement in radiographic score assignment, with further room for calibration on a dataset of several thousand reports. Next, we will correlate automated interpretations with actual clinical management decisions for radiation necrosis (e.g., initiation of steroids, bevacizumab, Laser Interstitial Thermal Therapy, and/or repeat imaging). This automated scoring system holds significant potential for LLMs in clinical applications. Future work will focus on integrating this model into clinical workflows and expanding its capabilities to include longitudinal monitoring of patient outcomes.

The Effect of Ambient Artificial Intelligence Notes on Provider Burnout.

Healthcare provider burnout is a critical issue with significant implications for individual well-being, patient care, and healthcare system efficiency. Addressing burnout is essential for improving both provider well-being and the quality of patient care. Ambient artificial intelligence (AI) offers a novel approach to mitigating burnout by reducing the documentation burden through advanced speech recognition and natural language processing technologies that summarize the patient encounter into a clinical note to be reviewed by clinicians. To assess provider burnout and professional fulfilment associated with Ambient AI technology during a pilot study, assessed using the Stanford Professional Fulfillment Index (PFI). A pre-post observational study was conducted at University of Iowa Health Care with 38 volunteer physicians and advanced practice providers. Participants used a commercial ambient AI tool, over a 5-week trial in ambulatory environments. The AI tool transcribed patient-clinician conversations and generated preliminary clinical notes for review and entry into the electronic medical record. Burnout and professional fulfillment were assessed using the Stanford PFI at baseline and post-intervention. Pre-test and post-test surveys were completed by 35/38 participants (92% survey completion rate). Results showed a significant reduction in burnout scores, with the median burnout score improving from 4.16 to 3.16 (p=0.005), with validated Stanford PFI cutoff for overall burnout 3.33. Burnout rates decreased from 69% to 43%. There was a notable improvement in interpersonal disengagement scores (3.6 vs. 2.5, p<0.001), although work exhaustion scores did not significantly change. Professional fulfillment showed a modest, non-significant upward trend (6.1 vs. 6.5, p=0.10). Ambient AI significantly reduces healthcare provider burnout and may enhance professional fulfillment. By alleviating documentation burdens, ambient AI can improve operational efficiency and provider well-being. These findings suggest that broader implementation of ambient AI could be a strategic intervention to combat burnout in healthcare settings.

Developing Linguistic Constructs of Text Readability Using Natural Language Processing

ABSTRACT Purpose Understanding what makes a text difficult to read is an important element of literacy instruction, materials development, and research into text readability. Readability formulas are often used to quantify text readability. However, readability formulas often focus on a relatively limited number of text features that inform the reading process and/or use single features to measure complex language constructs under the presumption that related features do not interact with one another. As a result, the formulas can be difficult to interpret by practitioners. Method A principal component analysis was used to combine text features from advanced natural language processing tools into theoretically-inspired language constructs related to text comprehension. Result Results indicate that text features aggregated into seven components related to informational text, syntactic constructions, noun phrase complexity, lexical ease, function word ease, narrativity, and lexical variety. These components predicted 44% of the variance in readability scores reported in a large readability corpus. Conclusion The results provide evidence that individual linguistic features related to text readability can be combined into reading components that are strong predictors of text comprehension. Practically, these components should be more easily interpretable allowing for more actionable feedback and use by practitioners.

Unveiling and advancing grassland degradation research using a BERTopic modelling approach

Grassland degradation presents overwhelming challenges to biodiversity, ecosystem services, and the socio-economic sustainability of dependent communities. However, a comprehensive synthesis of global knowledge on the frontiers and key areas of grassland degradation research has <pg=>not been achieved due to the limitations of traditional scientometrics methods. The present synthesis of information employed BERTopic, an advanced natural language processing tool, to analyze the extensive ecological literature on grassland degradation. We compiled a dataset of 4,504 publications from the Web of Science core collection database and used it to evaluate the geographic distribution and temporal evolution of different grassland types and available knowledge on the subject. Our analysis identified key topics in the global grassland degradation research domain, including the effects of grassland degradation on ecosystem functions, grassland ecological restoration and biodiversity conservation, erosion processes and hydrological models in grasslands, and others. The BERTopic analysis significantly outperforms traditional methods in identifying complex and evolving topics in large datasets of literature. Compared to traditional scientometrics analysis, BERTopic provides a more comprehensive perspective on the research areas, revealing not only popular topics but also emerging research areas that traditional methods may overlook, although scientometrics offers more specificity and detail. Therefore, we argue for the simultaneous use of both approaches to achieve more systematic and comprehensive assessments of specific research areas. This study represents an emerging application of BERTopic algorithms in ecological research, particularly in the critical research focused on global grassland degradation. It also highlights the need for integrating advanced computational methods in ecological research in this era of data explosion. Tools like the BERTopic algorithm are essential for enhancing our understanding of complex environmental problems, and it marks an important stride towards more sophisticated, data-driven analysis in ecology.

Optimizing ESG reporting: Innovating with E-BERT models in nature language processing

Developing a quantitative Environmental, Social, and Governance (ESG) rating tool using technology to reduce manpower requirements and ensure the objectivity and authenticity of the ratings is an important research question in the ESG field. The primary objective of this research is to develop an automated system, encapsulated in the Bidirectional Encoder Representation from Transformers for ESG rating (E-BERT) model, that evaluates ESG information with a high degree of objectivity and consistently delivers reliable rating outcomes. The E-BERT model, an advanced natural language processing (NLP)-based tool, is designed to transform ESG reporting by automating the evaluation process. Utilizing the architecture of Google’s BERT, this model offers precise and consistent ESG ratings, focusing on accurately assessing the sustainability contributions of enterprises. This research is initiated due to the absence of a comprehensive ESG dataset and involves constructing a tailored corpus that supports the E-BERT model. E-BERT meets the demand for objective ESG assessments by filtering out irrelevant data and standardizing criteria across various sectors, thereby streamlining the process and minimizing the need for manual intervention. This model not only automates the rating process but also achieves a notable 93% accuracy rate. By enhancing transparency and reducing biases, E-BERT marks a substantial improvement in ESG reporting, offering a robust tool for stakeholders to reliably assess corporate ESG performance. The success of the E-BERT model confirms its potential as a pivotal resource in supporting informed decision-making for sustainable development.

A hybrid machine learning and simulation framework for modeling and understanding disinformation-induced disruptions in public transit systems

Transportation infrastructure networks are prone to disruptions, most of which are beyond control. However, the spread of disinformation can worsen downtime in these systems by indirectly causing disruptions, such as station closures or rerouting of services based on false reports. The relationship between disinformation and the service disruptions is very important with reference to enhancing the resilience of transportation systems. This paper contributes to the field by applying artificial intelligence techniques to analyze how disinformation impacts service disruptions, particularly focusing on the Port Authority Trans-Hudson (PATH) system in New Jersey and New York, providing insights for improving operational responsiveness. The disruption operational impacts of disinformation are analyzed using several data sources, including schedules, ridership reports, and real-time alerts. A machine learning-based K-means algorithm framework is applied to cluster disruption alerts from social media. Disruption scenarios dominated by disinformation are identified using advanced natural language processing (NLP) methods, specifically BERTopic and Latent Dirichlet Allocation (LDA) topic modeling techniques. A Monte Carlo simulation is applied to quantify the effects of this dominant disinformation-induced disruption scenario on the commuter time and costs. This study reveals that disinformation significantly influences infrastructure reliability and points out the necessity for effective strategies to combat its impacts. The findings reveal the importance of transportation disruptions to the functioning of the transportation system and emphasize the need for robust measures to reduce the adverse effects, hence making the system to be more resilient and secure in the public’s perception.

ПЕРСПЕКТИВИ / МОЖЛИВОСТІ ЗАСТОСУВАННЯ CHAT GPT ДЛЯ СТВОРЕННЯ МЕТАДАНИХ БІБЛІОТЕЧНИХ РЕСУРСІВ

Advanced natural language processing technologies empower the development of intelligent systems capable of analyzing and comprehending text across various domains, including scientific publications, books, and other informational resources. This paper delves into the potential application of the artificial intelligence model ChatGPT within academic libraries, specifically focusing on metadata creation processes for library resources. Given the substantial resource investment required for metadata creation, description, cataloging, and adherence to globally recognized standards, the viability of leveraging modern technologies for such tasks is paramount. ChatGPT offers broad applicability in automating and enhancing the cataloging and description process of diverse documents. Serving as an artificial intelligence-based text generation system, ChatGPT can automatically generate metadata from textual descriptions of resources using sophisticated natural language processing algorithms. This capability streamlines and expedites resource cataloging processes, ultimately assisting library staff and information technology professionals in saving valuable time and effort. Furthermore, this paper discusses the potential of ChatGPT in generating metadata for various material types, ranging from scientific articles to websites and audio-visual recordings, while adhering to standards such as Dublin Core, MARC 21, and UNIMARK. Additionally, the article addresses potential challenges and limitations associated with using the ChatGPT model for metadata generation, including considerations of accuracy and text quality. Overall, this article explores a crucial aspect of applying artificial intelligence in the library field and highlights features and considerations concerning the use of the ChatGPT model for automatic metadata generation in library resources.