Snezhana Sulova has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Application of Natural Language Processing Technologies to Improve Accessibility of E-Learning Resources

    by Snezhana Sulova

    In the conditions of digitization, electronic educational resources are important to support the learning and development process. The accessibility of learning materials for disabled people plays a key role in ensuring universal education and ensuring equal access to knowledge for all, regardless of their individual needs and capabilities. The paper examines the application of natural language processing and text summarization technologies to improve the accessibility of electronic educational resources. The research focuses on the use of automated text processing methods to facilitate the access to information in electronic learning environments. Through the application of these technologies, better understanding and quick access to key information is achieved, thus improving the overall effectiveness and inclusiveness of e-learning resources. The research examines different approaches to text processing and summarizing, emphasizing the technical possibilities for optimizing the learning process and supporting students with different needs. The obtained results demonstrate the potential of integrating these technologies in e-learning to improve the accessibility and effectiveness of learning resources.


  • METADATA MANAGEMENT FRAMEWORK FOR BUSINESS INTELLIGENCE DRIVEN DATA LAKES

    by Snezhana Sulova, Olga Marinova

    Data lakes (DL) provide powerful capabilities for processing and utilizing large and diverse data, helping organizations adapt to the modern environment and extract maximum value from the information at their disposal. Effective data analysis provides actionable knowledge which is a competitive advantage for organizations. Metadata management in data lakes is a key element in ensuring their full functionality. At the same time, this is a dynamic and under-researched area that reflects the rapid development of information technology and the business needs for effective data management. The research is based on a thorough scientific analysis of existing publications on the chosen topic. For this purpose, up-to-date and relevant open access publications from Scopus and Web of Science that correspond to the keywords "data lake" and "metadata" are identified and are from the last 15 years. Based on a review of the existing literature, the main challenges in data lake metadata management are highlighted. The goal of the research is to summarize the existing models in the field of metadata management in data lakes and to propose a new conceptual framework that can serve as a useful guide for designing and implementing metadata management models in heterogeneous data warehouses, as well as implementation steps. The concept's adoption involves a detailed study of the data management model in a specific organization, a measurement of the level of effectiveness after the model’s implementation, and the use of additional metrics to confirm its feasibility. These tasks are therefore the subject of future research. Another limitation of the proposed framework is that it does not address in depth the rules and standards related to ensuring data security, which would be of the highest priority especially in sectors such as finance, defence and healthcare. In addition, further research could also focus on future analysis of the level of satisfaction with the transformation of metadata management processes.


  • Open Access

    An Approach for the In-Depth Data Analysis of the Marine Traffic of Independent Nearby Ports

    by Julian Vasilev, Snezhana Sulova

    Research background: Maritime transport helps the development of the economy of countries. Improving the current situation in this type of transport requires the application of modern software tools for assessment, analysis and forecasting. Purpose: The aim of this paper is to suggest an approach for an in-depth analysis of marine traffic near to independent ports. This approach is tested and validated for the Varna and Constanta ports for the period 2004–2021. Data from Eurostat are used. Research methodology: This paper proposes a new methodology for an in-depth analysis and forecasting of marine traffic of independent nearby ports using public data. Correlations, multiple regression, graphical methods, seasonality and trendlines are used to test and validate the proposed methodology. Results: The results show that the proposed methodology may be applied for other independent ports and periods. The results show some interesting facts about the analyzed ports of Varna and Constanta. Our initial assumptions that these two independent ports have similar seasonality is rejected. Novelty: The novelty of the paper refers to a new methodology for the in-depth analysis and forecasting of marine traffic of independent nearby ports using public data. Using the methodology in this paper (for an in-depth analysis of marine traffic of independent nearby ports) similar research may be done for other nearby ports and periods. Other research may focus on finding the specific types of cargo for each port influencing the differences in seasonality. Nearby ports with separate management may use the proposed methodology for better cargo planning and investment planning.


  • Open Access

    A Conceptual Framework for the Technological Advancement of E-Commerce Applications

    by Snezhana Sulova

    E-commerce is an area in which success largely depends on the e-commerce applications used. Currently, there are many studies that focus on various technological innovations in e-commerce systems, but a comprehensive concept of their improvement is lacking. In this regard, the main objective of the article was to explore the technological possibilities for the improvement of e-commerce systems and to propose a conceptual framework for their maintenance and development. The chosen research approach included a combined methodology–text mining analysis of existing developments and identifying the key themes and trends in papers and deep scientific analyses of the most-cited developments. As a result, a conceptual framework for the maintenance and development of e-commerce applications was proposed. To test the approach, publications from the scientific literature database Scopus, on the topic “e-commerce applications” were used. Experiments and text processing were performed with the software RapidMiner Studio. Several main directions for the development of e-commerce systems have been defined: the application of modern development tools; the technological base; and the possibilities of integration. Future research may focus on detailing each direction.


  • Open Access

    Approach for social media content-based analysis for vacation resorts

    by Snezhana Sulova, Boris Bankov

    The impact of social networks on our liveskeeps increasing because they provide content,generated and controlled by users, that is constantly evolving. They aid us in spreading news, statements, ideas and comments very quickly. Social platforms are currently one of the richest sources of customer feedback on a variety of topics. A topic that is frequently discussed is the resort and holiday villages and the tourist services offered there. Customer comments are valuable to both travel planners and tour operators. The accumulation of opinions in the web space is a prerequisite for using and applying appropriate tools for their computer processing and for extracting useful knowledge from them. While working with unstructured data, such as social media messages, there isn’t a universal text processing algorithm because each social network and its resources have their own characteristics. In this article, we propose a new approach for an automated analysis of a static set of historical data of user messages about holiday and vacation resorts, published on Twitter. The approach is based on natural language processing techniques and the application of machine learning methods. The experiments are conducted using softwareproduct RapidMiner.