Information Technology and Society

OPTIMIZING THE EDUCATIONAL PROCESS IN UNIVERSITIES USING CHATBOTS

2024-07-01T14:30:21+03:00

With the advent of technology, educational institutions are constantly looking for innovative ways to improve the learning experience for students. Chatbots have become a valuable tool for optimizing the educational process in universities, providing personalized assistance, quick responses to queries and seamless communication between students and teachers. Optimizing the educational process of the university with the help of a chatbot can greatly facilitate communication between students and teachers, as well as facilitate quick access to the necessary information. The chatbot can help students get answers to questions about the educational process, materials for preparing for tests and exams, and also provide general advice on studying. In addition, with the help of analytics, it is possible to identify weak points in the educational process and improve it. This analytics is possible through the use of external integrations with tools such as: Power BI, Tableau or Qlik Sense. Adding a chatbot to the university education system can improve the availability of information for students, promote their active participation in the educational process, and help solve possible problems quickly and efficiently. For example, a chatbot can answer questions about completing tasks, help with difficulties with educational material, or even conduct online consultations with teachers. Conclusions. A chatbot can become a student's digital assistant who is always ready to provide the necessary information and support. This will help to improve the quality of education, increase the motivation of students and increase the level of knowledge.

MODELING THE SURVIVABILITY AND RECOVERY OF INFORMATION AND COMMUNICATION NETWORKS IN THE FACE OF CYBER THREATS

2024-07-01T14:34:04+03:00

The article examines the pressing issue of centralization and hierarchization in information and communication networks (ICNs), which has led to the development of methods for assessing and addressing weaknesses in the physical and functional infrastructure of ICNs. The advancement of modern ICNs and the services based on them has resulted in such complexity and centralization that global systemic failures and cascading scenarios of ICN unavailability in the future become inevitable. It has been established that existing methods for modeling ICN recovery can be divided into two categories: recovery factor analysis and analysis of the structural and/or functional model of the system. It is proven that ICNs have a distributed architecture, but there is a tendency towards centralization and hierarchization. Attention is paid to the specificity of ICNs as an infrastructure object. The paper proposes a cognitive-emulation model for ICN recovery (CSM ICN), which is based on the general CSM CTS model and is used for comprehensive forecasting and scenario modeling of possible failures and unavailability scenarios of ICNs. CSM ICN utilizes a directed graph (digraph) to model ICN components and their connections. The model can be “network-centric” (emphasizing connections) or hybrid (adding “virtual nodes” for cause-and-effect relationships). Each node models a part of the ICN, its element, or working component. Nodes have characteristics that include recovery time and nature. The model uses the Burnbaum criterion to assess the impact of one element’s failure on others. Node recovery is modeled as a variable number of discrete time steps. The model uses three types of recovery functions for different levels of system readiness and has 4 levels of evaluation. The model can assess cascading scenarios where the failure of one element leads to failures in other parts of the ICN. Conclusions. Thus, modeling recovery and restart scenarios of ICNs will help identify potential vulnerabilities, analyze cascading scenarios of ICN unavailability in case of emergencies and natural disasters. The application of CTS ICN will significantly increase the resilience and operational stability of ICNs in conditions of external attacks, personnel errors, and the impact of other emergencies and force majeure events.

A CHAT-BOT FOR PROVIDING RECOMMENDATIONS FOR WATCHING VIDEOS BASED ON MATRIX FACTORIZATION MODELS

2024-07-01T14:39:53+03:00

The article examines the main models of predicting user reactions in recommendation systems based on matrix factorization methods. The choice of the matrix factorization model is justified and the approaches to ensuring the flexibility of interaction between the recommendation system and the user through the use of a chatbot implemented in web applications are considered. The purpose of the article is to study the effectiveness of using a chatbot in providing personalized recommendations for viewing video content on the basis of a matrix factorization model. Research methods. General methods of developing web applications and intelligent chatbots are used, methods of matrix factorization using SVD sigular value decomposition method, machine learning methods, natural language processing and recognition methods, and recommendation system optimization methods based on assessment of forecast accuracy, satisfaction level of communication with the chatbot. The scientific novelty of the study consists in the identification of methods and approaches aimed at improving users' receipt of personalized recommendations for watching video content in accordance with their interests and preferences by using a chatbot and a model for predicting user reactions based on matrix factorization methods. Conclusions. The accumulation of large volumes of digital video information in various formats requires the improvement of mechanisms for providing recommendations and increasing the accuracy of providing predictions regarding user preferences. The research of the matrix factorization models MF, the factorization machine FM, and the field-aware factorization machine FFM made it possible to establish that the model of the field-aware factorization machine FFM had the best indicators of forecast accuracy: MAE=0,86, MSE=1,65, RMSE=1,28. To ensure the flexibility of user interaction with the recommendation system developed on the basis of the FFM model, the expediency of its integration with a chatbot implemented in the web application was found. The research of the quality of the created natural language processing model showed a high accuracy of recognizing the user's intentions when communicating with the chatbot - 99.17%. Detection of the level of user satisfaction with communication with the chatbot and received recommendations made it possible to establish that user satisfaction was 86.6%. Which indicates a high level of assessment of the effectiveness of user interaction with the chatbot and the high accuracy of the system in terms of predicting users' intentions to watch videos.

STUDY OF THE EFFECTIVENESS OF THE MODIFIED METHOD OF AUTOMATED SEARCH FOR KEYWORDS IN TEXT

2024-07-01T14:44:15+03:00

In the conditions of constant growth of the volume of text data, which a person has to process in almost all spheres of his activity, the task of ensuring quick access to the necessary information becomes extremely important. To solve this problem, existing search engines, as a rule, perform data indexing: special bots scan resources and try to find keywords related to them. The relevance of the search results that will be issued to the user of the search engine directly depends on the correctness of the keywords found. This article discusses a modified method of automated search for keywords in natural language text data. It is based on the analysis of complex syntactic relationships between words in the sentences of the text and is able to search for key terms consisting of several words. The research objective is the programmatic implementation and experimental study of the effectiveness of the modified method of automated search for keywords in text data. Methodology of implementation. For testing, the modified method was implemented on the Python NLTK platform. Two sets of texts were chosen as a test dataset: texts of a small volume (up to 400 words) and texts of a larger volume (up to 2500 words). Comparisons were made with three popular analogues, each of which is implemented on the basis of different approaches (machine learning, N-gram analysis, statistical analysis). For quantitative measurement of efficiency and comparison with existing analogues, it is proposed to use absolute accuracy and completeness metrics according to Jaccard. Conclusions. The results of the tests demonstrated the superiority of the proposed method over analogues in the accuracy of searching for keywords. It was noted that with an increase in the volume of texts, the absolute accuracy increases in almost all cases, but the completeness according to Jaccard decreases. Based on the test results, further directions of work on improving the proposed method are formulated.

REVIEW AND ANALYSIS OF RESEARCH ON THE ISSUES OF INFORMATION SECURITY OF CLOUD INFRASTRUCTURES

2024-07-01T14:47:14+03:00

Cloud computing is an access to network resources, such as data storage and computing power, on demand, without direct control by users. Currently, cloud computing includes both public and private data centers that provide customers with a single platform over the Internet. Peripheral computing (edge computing) is a strategy aimed at bringing computing and information storage closer to end users, reducing response time and optimizing the bandwidth of cloud services. Mobile cloud computing uses distributed computing to deliver applications to mobile devices such as phones and tablets. Numerous studies show that cloud computing and mobile cloud computing face information security (IS) challenges, threats, and vulnerabilities for customers, and one of the promising methods to combat these threats is the use of machine learning (ML) techniques. In this article, an analysis of IS threats and problems is carried out, as well as a review of the solutions proposed by various authors for the IS provision of cloud computing and cloud services. First of all, research based on the application of MN algorithms to ensure the security of cloud computing and cloud services is considered.

AUTOMATION OF THE INFORMATION ASSETS MODULE

2024-07-01T14:50:20+03:00

The article examines in detail the process of automating the information assets module as a key stage in ensuring effective management of information security in modern organizations. The main emphasis is on the use of ORM frameworks, in particular Hibernate, as a means of simplifying access to the database and optimizing the management of information resources. The purpose of this article is to study the possibilities of increasing the level of security of information assets through the automation of their management module. To achieve this goal, the methodology of developing and implementing a software module based on the Hibernate ORM framework and the Java Persistence API was used. The article describes in detail the stages of development and implementation of the module, including inventory, categorization and automation of asset management. An overview of the main benefits of using Hibernate, such as improved system performance and reliability, is provided. The criteria for the effectiveness of the developed solution were analyzed in detail, including reliability, security, speed of operation and availability. Scientific novelty consists in the application of modern technologies to increase the efficiency and reliability of information security management. It was concluded that the automation of the module made a significant contribution to improving the efficiency of information security management and facilitating the use of the system. The conclusions of the article confirm the success of using ORM frameworks for automating the management of information assets, which leads to improved efficiency and ensuring a high level of data protection.

LAMBDA CALCULUS TERM REDUCTION: EVALUATING LLMS' PREDICTIVE CAPABILITIES

2024-07-01T14:53:14+03:00

This study is part of a research series of optimizing compilers and interpreters of functional programming languages. Lambda Calculus was chosen as the most straightforward functional programming language, which can process any operation available to other functional programming languages but with the simplest syntax. Using machine learning methods allows for uncovering relations inside lambda terms, which might indicate which reduction strategy better suits their reduction. Finding those techniques for lambda terms allows optimizing not only lambda term reduction but also interpreters and compilers of functional programming languages. This research aims to scrutinize LLMs' understanding of Lambda term reduction to predict reduction steps and evaluate prediction accuracy. Artificially generated Lambda terms were employed Utilizing OpenAI's GPT-4 and GPT-3.5 models. However, due to model constraints and cost considerations, experiments were limited to terms with specific token counts. Despite its larger size, results revealed that the GPT-4 model did not significantly outperform GPT-3.5 in understanding reduction procedures. Moreover, while the GPT-3.5 model exhibited improved accuracy with reduced token counts, its performance with more complex prompts was suboptimal. This underscores the LLMs' limitations in grasping Lambda terms and reduction strategies, especially with larger and more intricate terms. Conclusions. The research concludes that general-purpose LLMs like GPT-3.5 and GPT-4 are inadequate for accurately predicting Lambda term reductions and distinguishing between strategies, particularly with larger terms. While fine-tuning may enhance model performance, the current findings highlight the need for further exploration and alternative approaches to achieve a deeper understanding of lambda term reduction using LLMs.

METHOD OF BUILDING SOFTWARE DETECTORS FOR DETECTING SOFTWARE BOTS IN SOCIAL NETWORKS

2024-07-01T14:55:56+03:00

The purpose of this work is to study in detail the effectiveness of using large language models (LLM) to detect software bots in social networks. The work focuses on analyzing the effectiveness of different detection methods and determining the potential of LLM as a means to improve the accuracy and efficiency of the bot identification process. The study covers the analysis of three main approaches to bot detection: metadata analysis, text analysis, and graph analysis. Both traditional machine learning methods and the latest LLM are analyzed for their ability to analyze big data from social networks. The main technique is benchmarking, which involves the use of extended datasets such as TwiBot20 and TwiBot-22 to evaluate the performance of each method using metrics such as accuracy and F1-measure. It provides an objective view of the performance of different approaches to bot detection. The scientific novelty of this work is the use of LLM to analyze various types of data from social networks to detect software bots. The authors consider the integration of LLM into traditional detection methods, which allows adapting detection processes to the complex behavior of software bots, ensuring high accuracy and efficiency. Conclusions. LLMs demonstrate high efficiency in detecting software bots, outperforming traditional methods by some indicators. However, given the computational demands of LLM, the authors recommend considering hybrid approaches that combine the advantages of LLM with the efficiency of traditional methods to optimize resource usage and provide a more robust and adaptive bot detection system. This approach can improve the overall performance of bot detection systems, reduce computing resource costs, and provide more accurate and effective detection of malicious actors in social networks. Further research is recommended to improve the integration of LLM into bot detection systems, especially in the context of the dynamic behavior of social networks and the evolution of software bots.

ALGORITHMS IN SOFTWARE SOLUTION FOR AUTOMATED USER INTERFACE TRANSLATION

2024-07-01T15:10:19+03:00

Numerous daily activities are long since accomplished using mobile applications and international resources available through the Internet. This raises the issue of the need for end users to know the languages required to operate and use these programs. Not every developer in the world has access to professional translation services, or the ability to create such translations on their own. An important and usually determining factor is the cost of translation software. Large professionally-targeted software packages have license fees measured in hundreds of US dollars. Also, the majority of existing solutions are meant for various kinds of general freeform text. An alternative approach would be hiring teams of translators, but this needs accounting for the extra time and size of translation, as well as limited availability of translators for the lesser known world languages. Evaluating these factors shows an existing need of a convenient and accessible program specialized in creating and ensuring quality translation of software user interfaces specifically. Analysis leads to confirmed requirements for the program, those being a comfortable user interface and a set of functions specific to working with user interfaces and source code files. The purpose of this work is to develop software that meets the functionality requirements for automated user interface translation. Methodology. Software is developed using the C# language and Microsoft Visual Studio environment. The program’s interface was designed according to needs of software developers. Scientific novelty. Determine ways and approaches to improve existing methods and tools, and the development of software to provide a new tool for translation. This work describes the development of such software tool for Microsoft Windows that implements every listed requirement for base functionality. The program is specialized for translation of user interfaces and enables automation of the process. The process of providing user interface translation for software created by small teams of developers were optimized and simplified via a full link to existing source code regardless of programming language used. Conclusions. The developed program can be used to create and translate user interfaces. Machine translation functionality requires possession of a personal key to utilize Google Translate API.

EXPLORING THE IMPACT OF BIG DATA ANALYTICS ON BUSINESS PERFORMANCE IN THE DIGITAL ERA

2024-07-01T15:22:33+03:00

The corporate world is benefiting from the trends of BIG DATA (BD) and business modeling and analysis. Previous studies have demonstrated the enormous and exponential growth of data created in the modern world. These consist of the everyday inundation of unstructured and structured information in companies. Problem statement. The main research gap addressed by previous literature studies is the lack of a comprehensive analysis of BD's application for digital transformation. Purpose of study. This is filled by looking at the strategic benefits, opportunities, and challenges that BD presents to companies as they digitally transform their IT platforms. Therefore, the purpose of this study is to draw attention to the numerous uses and advantages of the technology of BD among researchers and companies. Methodology. Qualitative Research Methods, Utilizes qualitative research methods for a broad perspective. Emphasizes exploratory research to advance knowledge in the field. Uses an epistemological approach to find relevant literature sources from reputable databases like Google Scholar and Science Direct. Scientific novelty. Based on the research that is currently accessible, the article evaluates and discusses the latest trends, possibilities, and dangers of BD and how it has helped firms stay competitive by enabling them to develop successful business strategies. The assessment also covers the several uses for BD and analytics in business, as well as the data sources that are produced and their salient features. Conclusion: Lastly, the paper not only describes the difficulties in putting BD projects into practice successfully but also points up open research paths in BD analytics that need further attention. According to the BD topics under evaluation, effective administration and manipulation of massive data sets utilizing BD techniques and technologies may produce valuable business insights.

DEVELOPMENT OF A MOBILE APPLICATION TO SUPPORT THE PROVISION OF ENERGY MICROGRID SERVICES

2024-07-01T15:25:56+03:00

The purpose of the work is to develop a mobile application for informing customers of energy networks about the state of operation of the networks, as well as about the forecasted volumes of electricity generation from renewable sources. Methodology. To study the relevance of using mobile applications to gain access to information about the current and projected state of energy networks, an analytical method was applied, which includes the search and analysis of relevant scientific literature, the study of existing mobile applications, as well as the establishment of functional requirements for the mobile application. The methods of structural-functional modeling are used to represent the system in the form of functions that are related to each other and functions that transform input data into output. The design method was used in the development of UML use case diagrams. For the practical implementation of the mobile application, a methodology using the principle of Clean Architecture was chosen. The results. An overview of modern trends in the development of mobile applications, including for monitoring and managing energy networks, was conducted. Modeling of the mobile application use case was carried out, as well as modeling of the sequence of actions of the main actors in working with the mobile application using the UML language. The mobile application is developed for the Android operating system to work with energy network data stored in the SQLite database management system. The screens of the mobile application - authorization, location selection, and the main screen, which displays information about the energy microgrid at the selected location, were designed and implemented. The operation of the mobile application to support the provision of services from electric microgrids to a client with two microgrids installed in different locations has been tested. The scientific novelty lies in the fact that the developed mobile application has such an architecture that allows integration into the decision support system for managing energy microgrids and displaying data from a single database of the information system through the API interface. Conclusion. The work presents the development of a mobile application for user monitoring of the current state of the energy microgrid, as well as informing about the forecast volumes of electricity generation.

PRACTICAL ASPECTS OF INFORMATION WARFARE IN ONLINE DOMAIN

2024-07-01T15:29:48+03:00

The given article studies information warfare in the online domain as one of the aspects of contemporary life. Information warfare, which has been carried out by the hostile russian federation for a long time not only in the information space of Ukraine, but other countries all over the world, got a full swing with the full-scale invasion. Studying this problem from a new perspective is crucial, which defines the novelty of the given work The aim of the article is to analyse the ways of using information as a weapon to achieve diverse objectives, including political, economic and social. It emphases that the primary goal of information warfare is not the physical destruction of individuals, but the dismantling of their social cohesion. Metodology. Having analysed numerous media sources, there have been revealed the main approaches to conducting information warfare in the online domain, such as the creation and dissemination of disinformation, the use of social media, cyberattacks, and propaganda. The article emphasizes the significance of critical thinking and fact-checking in combating misinformation. It also describes the use of information as the information warfare weapon, focusing on troll factories, bots, social media, and cyberattacks, and how they can be used to manipulate public opinion, encourage social movements, and influence political, social and cultural relations in the society. The article considers the impact of cyber espionage and hacker attacks on various targets, particularly governmental institutions, corporate networks, and personal computers of ordinary users. In the context russian-Ukrainian war hacker attacks and cyber espionage have become pivotal tools of warfare. Russian malicious actors actively employ these methods to target Ukrainian information systems to steal or destroy confidential information. The main aim of information warfare predominantly is to disrupt the exchange of reliable information and induce panic among the Ukrainians. Russian propaganda actively disseminates manipulative news and employs hyperboles to show Ukrainian military personnel and displaced persons in a negative light. Conclusions. The article focuses on necessity to develop and improve efficient strategies for dealing with cyberattacks, such as the use of robust software, regular system updates, data backup and raise of public awareness about information security and hygiene. The authors of the article call for a balanced approach to ensuring national security and preserving fundamental human rights, as well as creating effective ways to resist various cyber threats.

IMPROVING NOISE IMMUNITY AND INCREASING DATA TRANSMISSION SPEED IN WI-FI NETWORKS

2024-07-01T15:34:33+03:00

Wireless communication systems, including computer Wi-Fi networks, are currently undergoing intensive development. The radio communication channels of such systems are subject to a complex of interference and distortion. To improve such parameters as performance and interference resistance, especially in conditions of dense use of a rather limited frequency channel, there is a need to improve existing methods and create fundamentally new ones. The purpose of the article is to review the methods of information transmission in modern wireless access systems and to study algorithms for increasing network capacity by applying adaptive spatial signal processing methods and finding a balance between increasing the throughput of MIMO technology and reducing the probability of reception errors. Research methods: the study uses methods of information transmission in modern wireless access systems and algorithms for increasing network capacity. The scientific novelty of the study is that the analysis of modern methods of wireless information transmission revealed that space-time coding successfully combines the advantages of spatial diversity methods with the ability to correct errors with a corrective code when using optimal decoding algorithms, while the effectiveness of research and development of new methods of space-time coding largely depends on how well the channel models match real-world conditions. One of the promising methods for improving network quality parameters is the method of synthesizing convolutional-block signal-code structures using internal signals from the class of space-time block coding and external signal structures, which is an effective technique for reducing the effect of fading on signals, improving the quality and throughput of the Wi-Fi communication system. Conclusions. The development of these algorithms and methods opens up broad prospects for the future development of wireless communication systems. One of the key prospects is to further improve the methods of adaptive spatial signal processing and optimize the balance between increasing throughput and reducing the probability of reception errors. Additionally, the capabilities of convolutional-block signal-code designs can be expanded by researching and implementing new technologies, such as using machine learning to optimize signal coding and decoding parameters. There are also opportunities to apply these techniques to high-speed mobile networks, such as fifth generation (5G) and future generations, where high bandwidth and data efficiency are becoming key requirements.