Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Radka Nacheva has a total of 36 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Graph-Enhanced LLM Architecture for Reliable Data Management: Design Principles and Proof of Concept

    by Otmane Azeroual, Radka Nacheva

    Large Language Models (LLMs) demonstrate significant capabilities in natural language understanding, generation, and reasoning, yet their deployment in structured data contexts is hindered by hallucinations, limited explainability, and unreliable outputs. This paper presents a Graph-Enhanced LLM Architecture that integrates structured knowledge graphs with LLMs to provide traceable, auditable, and explainable responses for AI-assisted data management. The proposed architecture combines natural language interpretation, graph-grounded retrieval, schema-aware validation, and retrieval-augmented generation (RAG) in a modular pipeline. Beyond the conceptual architecture, the paper includes a proof-of-concept implementation and a small feasibility demonstration illustrating how graph grounding improves factual support and traceability for representative data management queries. The primary contribution lies in the architectural design principles and integration strategy for graph-enhanced LLM systems. A comprehensive large-scale empirical benchmark evaluation is left for future work.

  • ADAPTIVE MICRO-SUPPORTS (“NUDGES”) FOR STUDENT MOTIVATION: A REINFORCEMENT LEARNING APPROACH ACROSS THE SEMESTER

    by Jose Paulo Machado da Costa, Ana Sofia Coelho, Oliva Maria Dourado Martins, Radka Nacheva

  • Open Access

    A CRISP-DM and Predictive Analytics Framework for Enhanced Decision-Making in Research Information Management Systems

    by Otmane Azeroual, Radka Nacheva, Anastasija Nikiforova, Uta Störl

    The age of digitization has led to a significant increase in the amount and variety of data, particularly within the research domain, where data previously stored in paper form has now been digitized and integrated into research management processes. The rapid growth of Big Data, driven by technologies like the Internet of Things, presents challenges for conventional data processing methods. However, data alone, stored in silos, lacks value. To unlock its potential, data must be analysed and processed to generate insights and predictions that enable evidence-based decision-making. Predictive Analytics (PA) is a powerful tool for this purpose. By leveraging PA and advanced statistical methods, predictive models for research management can be developed, helping to forecast research trends and outcomes, which in turn, provides decision-makers with a reliable, forward-looking basis for strategic decisions in research management. This paper explores the application of PA in Current Research Information Systems (CRIS) to enhance decision-making. A case study using metadata from 20,000 publications indexed in Scopus demonstrates how PA can identify emerging research topics and predict future trends. Machine learning algorithms such as Support Vector Machine (SVM), k-Nearest Neighbor (kNN), Random Forest, and Tree classifiers were employed, with metrics such as Area Under ROC (AUC), classification accuracy (CA), F1-score, precision, and recall evaluated. The results indicate that the kNN algorithm provided the highest performance with an AUC of 0.451 and a classification accuracy of 87.4%. These results show that predictive models can reveal significant patterns in research data, supporting data-driven decisionmaking for research management. Additionally, the study applied Latent Semantic Indexing (LSI) and clustering techniques to identify and categorize key topics within the data, showing a thematic focus on areas such as smart cities and urban intelligence before predictions, and CRIS applications after predictions. The findings illustrate how PA can optimize research management by identifying gaps in research and forecasting emerging topics, thereby aiding institutions in making more informed, evidencebased decisions


  • Open Access

    Analysis of AI Mobile Applications for Ensuring Digital Accessibility in Higher Education for People with Disabilities

    by Radka Nacheva

    Introduction: Over 1 billion people worldwide have disabilities, necessitating their inclusion in health systems and workplaces. Artificial intelligence (AI) is revolutionizing accessibility and digital inclusion for these individuals, improving everyday tasks and enabling autonomous mobility. AI can be applied to visually impaired, reduced mobility, and cognitive disabilities, supporting their inclusion in learning and work environments, and promoting social and digital inclusion. Methods: The study investigates mobile applications for disabled individuals in higher education, utilizing readability analysis of texts generated using Otter.ai, using qualitative methods to assess the accessibility of AI-generated samples. Results: Results show that the auto-generated text’s readability is about or below average level. Discussion: The text, tailored for computer science students, emphasizes human-computer interaction and user interface (UI) usability, utilizing specialized terms and real-time recording for hearing impairments. Limitations: The data of this study were collected only from Otter.ai based on the narration of part of a computer science-related lecture. No other AI tools are used for automatic text generation. Conclusions: Based on the analysis, we made changes to the AI-generated content, cutting down lengthy paragraphs, simplifying complicated words, and utilizing straightforward language without compromising the intended message.


  • Framework For Training and Development in The Human Resource Management System: Implementations and Tools

    by Radka Nacheva

    This study examines the key role of training and development in human resource management systems, emphasizing the need for an integrated, dynamic framework aligned with the strategic goals of the organization and the individual competencies of employees. This paper aims to develop a model of a gamified training and development system that will increase the engagement and motivation of personnel in organizations. The study uses an analytical-descriptive approach in combination with quantitative methods for needs assessment and system design. An analysis of existing training practices, digital platforms, and adaptive technologies was carried out. The study includes modeling of key functionalities of a gamified system. Competency assessment, system analysis, and prototyping methods were used. The developed model integrates elements of gamification to stimulate active participation. The results of the expert evaluation of the model show the potential for the need to increase participation, effectiveness, and satisfaction of learners. The proposed model contributes to the development of modern human resources management practices by integrating digital solutions and behavioral incentives.

  • Open Access

    Trends and best practices for ensuring digital accessibility in the workplace

    by Radka Nacheva

    Digital accessibility in the workplace is essential for creating an inclusive environment where all employees can fully participate. Trends include AI-powered accessibility solutions, voice user interfaces (VUI), mobile accessibility, inclusive design practices, and adhering to global accessibility standards like the Web Content Accessibility Guidelines (WCAG). Inclusive design goes beyond accessibility compliance, considering diverse user needs from the start of the design process. Global accessibility standards are increasingly adopted to ensure a consistent and globally inclusive digital workplace. Best practices for promoting digital accessibility include accessibility training for all employees, active involvement of people with disabilities in user testing, creating accessible documents, choosing collaboration and communication tools, conducting regular accessibility audits, designing and maintaining internal websites and intranet platforms, establishing clear accessibility policies and guidelines, implementing employee feedback mechanisms, and ensuring leadership commitment to fostering a culture of accessibility. Organizations can create a digital workplace that is not only accessible but also promotes a more inclusive and diverse work environment. In this regard, the paper aims to explore the global trends and good practices related to digital accessibility by deriving recommendations for ensuring digital accessibility in the workplace.


  • AI Chatbots for Competency-Based Training in Programming Languages Courses

    by Radka Nacheva, Iviana Hristova

    Competency-based training (CBT) is a specialized method for teaching programming languages, focusing on mastering new skills through time-based development. It emphasizes specialized skills in information and communication technologies (ICT), such as logic, syntax comprehension, debugging, and algorithm creation, rather than memorizing information. CBT provides a customized learning experience by integrating real-world problem-solving into the curriculum. AI-powered chatbots can track students' progress, target weaknesses, and offer immediate feedback. Benefits of CBT include increased skill competency, better retention rates, and improved student engagement. However, issues include the need for well-thought-out competence frameworks, resource-intensive implementation, and continuous evaluation of AI's contribution to education. In this sense, insights into best practices in applying CBT frameworks in computer science education are studied in this paper, as well as the integration of CBT with AI-powered chatbots in programming courses is proposed.


  • Open Access

    Profile of urban sustainability in Bulgaria

    by Margarida Rodrigues, Mário Franco, Hristina Filipova, Rui Jorge Silva, Velina Kazandzhieva, Radka Nacheva, Velina Koleva, Lyubomir Lyubenov, Cidália Oliveira, Ana Pinto Borges, et al.

    Sustainability is becoming increasingly relevant due to the need to decide on planned management of land use and natural resources as well as sustainable development in the context of cities. This study aims to identify indicators for measuring the sustainable development of districts/countries in Bulgaria. Using the Multivariate Analysis (MVA) method, where we examine multiple variables in several dimensions, the results show that in the environmental pillar, the management of natural resources, including water and soil, was under pressure due to industrial and urban activities. Air quality and waste management were also critical issues in some urban areas. The promotion of sustainable building practices and the adoption of renewable energies could be areas of focus for improving environmental sustainability in Bulgarian cities. This study is innovative becouse it underscores the imperative need for urban sustainability to integrate the foundational pillars of sustainability harmoniously. Central to this integration is the cultivation of economic growth that upholds environmental integrity and fosters social equity and opportunity. More theorectical and managerial contributios are also presented.