A Cyclical Approach to Legal Document Analysis: Leveraging AI for Strategic Policy Evaluation⋆ Khrystyna Lipianina-Honcharenko1, †,*, Nataliia Maika1, †, Svitlana Sachenko1, †, Lukasz Kopania2, † and Mariana Soia1, † 1West Ukrainian National University, Lvivska str., 11, Ternopil, 46000, Ukraine 2Kazimierz Pulaski University of Technology and Humanities in Radom, Department of Informatics, Jacek Malczewski str., 29, Radom, 26600, Poland Abstract This article presents an approach to the analysis of legal documents that integrates artificial intelligence (AI) technologies to optimize processes of data extraction, classification, and compliance assessment to legal norms. With a focus on the accuracy of analysis, the study demonstrates how the application of advanced machine learning algorithms and natural language processing can significantly enhance the quality of legal text processing. The results show the AI algorithms' average weighted accuracy in analyzing AI development strategies by countries and categories at 0.91, with the highest accuracy in the "Specific Targets" category (1.0) and "AI Development Strategy" (0.99), indicating a high potential for AI application in legal analytics. These findings underscore the need for further research to optimize AI algorithms aimed at improving analysis accuracy in complex legal domains. Keywords Artificial intelligence, Legal analysis of documents, Natural language processing, Machine learning. 1. Introduction Today, it is practically impossible to imagine our lives without using artificial intelligence (AI) in the modern world. In his blog, Bill Gates concluded that the widespread use of neural networks will be possible by 2030, with AI tools being used everywhere in the USA in just 1.5 years, and in African countries — in 3 years. The co-founder of the technology corporation emphasizes that preparations are still underway for a technological boom [1]. Developed and developing countries have already approved national programs and AI development plans, which indicates an awareness of the role of new technologies in the development and functioning of states and, in perspective, the formation of a humane digitized environment. Moreover, most governments declare their leadership in technology development (namely by attracting significant investments in research and focusing on the development of technologies ICyberPhyS-2024: 1st International Workshop on Intelligent & CyberPhysical Systems, June 28, 2024, Khmelnytskyi, Ukraine ∗ Corresponding author. † These authors contributed equally. mailto:xrustya.com@gmail.com (K. Lipianina-Honcharenko); N.Maika_law@meta.ua (N. Maika); as@wunu.edu.ua (S. Sachenko); l.kopania@uthrad.pl (L. Kopania); mariankasoa@gmail.com (M. Soia) 0000-0002-2441-6292 (K. Lipianina-Honcharenko); 0000-0002-5676-980X (N. Maika); 0000-0001-8225-1820 (S. Sachenko); 0000-0002-7318-4803 (L. Kopania); 0009-0001-3719-6460 (M. Soia) CEUR ceur-ws.org Workshop ISSN 1613-0073 Proceedings in the field of national defense). It is projected that by 2030, the economic benefits of using AI will be greatest in China and North America, which will constitute 70% of the global economic impact of AI [2]. AI is one of the key technologies of the new stage of economic development (known as "Industrial Internet of Things" or "Industry 4.0"), and the formation of a new society ("Super Smart Society or Society 5.0"). The implementation of AI technologies influences a country's competitive potential, especially regarding national security and defense, industrial, and social development. A country's approved development strategy, serving as the foundation of a defined policy course regarding the regulation and introduction of new technologies, is a means to minimize the threats and challenges associated with the development of these technologies. The integral map of concepts for the development of new technologies is diverse and distinct. Despite the similarity of general tasks, principles, and methods, these strategies must each time be adapted to unique conditions, leading to different paths toward the more or less similar general goals of the international community. Therefore, a hot problem is the analysis of AI development strategies (of developed and developing countries) regarding key aspects of development and legal implementation at the national level. Considering the above and the relevance of the research, this article presents a new cyclical approach to the analysis of legal documents, based on the application of advanced AI algorithms. The aim of the study is to develop a comprehensive method that will automate the processes of analysis, classification, and assessment of compliance of legal documents with established norms and standards. It is demonstrated how the application of this approach can optimize the processes of working with legal texts, improve the accuracy of their analysis, and contribute to effective decision-making in the legal sphere. The study also emphasizes the importance of regulation and standardization in the use of AI technologies in jurisprudence, considering potential threats to data confidentiality and security. The structure of this work is organized in such a way that it initially presents a review of existing AI research and technologies used in the legal field, and then describes in detail the developed cyclical approach and its implementation through a series of stages of legal document analysis. The conclusions emphasize the significance of the obtained results and the prospects for further research in this area. 2. Related Work The advancement and expansion of AI over the years have been fostered by a continuous search in algorithms, machine learning methods, and integrating statistical analysis into understanding the world at large [3]. The field of science and technology, particularly in AI inventiveness and creativity, had earlier been subjected to human intervention. However, with the recent development in AI and the era of «big data», machines can now invent devices and processes autonomously [4]. This has led to an endless application of artificial intelligence in several sectors and industries such as healthcare, real estate, entertainment, logistics and transport, banking and financial services, travel, retail and e-commerce, manufacturing and food technology [5]. The field of jurisprudence is no exception too of using AI. The topic of technology in the legal sphere is quite extensive, which creates the need to investigate all relevant events and processes that currently have the greatest impact on the legal system and social relations [6] Legal technology encompasses the use of various technological tools and innovations to improve legal practice, enhance legal processes, and facilitate better access to justice. These technologies aim to improve efficiency, accuracy, and accessibility in the legal field [7]. The majority of the resources in this field are presented in text forms, such as judgment documents, contracts, and legal opinions. Therefore, most Legal AI tasks are based on Natural Language Processing (NLP) technologies. Many tasks in the legal domain require the expertise of legal practitioners and a thorough understanding of various legal documents. Almost all models are better at case analyzing than knowledge understanding, which proves that knowledge modelling is still challenging for existing methods. How to model legal knowledge to LQA is essential as legal knowledge is the foundation of LQA [8]. The use of AI in jurisprudence opens new horizons for litigation, legal analysis, and the administration of justice. Research in this field shows that AI can help reduce search time, improve quality, and effectively extract relevant information from expanding textual sources, such as decisions of Brazilian courts [9]. In the context of the Indian judicial system, AI is used for data storage and retrieval, multi- party litigation systems, online dispute resolution platforms, and even predicting court decisions [10]. The need for regulation of AI technologies in jurisprudence is critical for standardizing policy and assessing data privacy threats [11]. AI can also be implemented in justice as a psychological phenomenon, integrating legal and psychological aspects to establish the limits of its application in law enforcement activities and court proceedings [12]. The emergence of AI-related crimes poses global challenges to jurisprudence, prompting potential improvements in legislation to respond to these new types of criminal activity [13]. Research in the field of document analysis with cyclical processing, information extraction, machine learning, and NLP demonstrates a wide range of applications and methodologies. The study [14] considers the analysis of citations using NLP and ML techniques to assess the impact of citations in scientific assessment. In [15], different approaches to keyword extraction and synonym generation are explored, highlighting the benefits of the extreme learning model. In [16], the application of NLP and ML to patient reviews is analyzed, [17] focuses on text classification in multi-turn corpora, and [18] investigates deep learning for document analysis. These studies highlight the significant potential of NLP and ML in diverse applications, from analyzing reviews to classifying texts. Below is a comparative Table 1 of approaches and quantitative assessments of the closest analogues among scientific articles. Compared to the closest studies [24-26], this study demonstrates higher accuracy (0.91) in the analysis and classification of legal documents due to the integration of advanced machine learning and natural language processing algorithms. Therefore, this study not only ensures high accuracy of analysis but also shows better adaptation to various aspects of legal documents, making it a more efficient and reliable tool for legal analysis and strategic policy evaluation. Table 1 Comparative Analysis of Closest Analogues Study Approach Quantitative Assessment [24] Use of AI-based software to improve No specific numerical values given, but a speed and accuracy of analysis significant increase in speed and accuracy noted [25] Implementation of deep learning for text Classification accuracy: 0.87, classification in legal document review performance across multiple document classes [26] Integration of AI and machine learning Prediction accuracy: 0.89, improvement for document analysis and accuracy in document analysis accuracy prediction 3. Approach to the analysis of documents with cyclic processing The approach to analyzing documents and extracting relevant information can be considered a sequence of operations that includes text analysis, pattern recognition, and data categorization. The objective is to transform unstructured textual data (documents) into a structured format (table) based on predefined categories. This includes several steps: 1. Text Preprocessing [19]. Before analyzing documents, it is necessary to convert them from raw text data into a format that is easily processed. This process includes [20] • Tokenization: the division of text into words or phrases. • Normalization: converting text to a uniform case, removing punctuation. • Stemming or Lemmatization: reducing words to their base or root form. These steps simplify the text and facilitate the detection of patterns. Formally, for a set of documents 𝐷𝐷 = {𝑑𝑑1 , 𝑑𝑑2 , … , 𝑑𝑑𝑚𝑚 }, each document 𝑑𝑑𝑖𝑖 is subjected to preprocessing to obtain the processed document𝑑𝑑𝑖𝑖′ . 2. Feature Extraction [21]. The process of identifying text attributes that may indicate its relation to predefined categories. Mathematically, this is described as: transforming the text data 𝑑𝑑𝑖𝑖′ into a feature vector𝑥𝑥𝑖𝑖 ∈ 𝑅𝑅𝑛𝑛 , where each dimension corresponds to a separate feature. This step converts the text into a form suitable for machine learning analysis. 3. Classification [22, 27, 28]. The use of document features to classify it into predefined categories using machine learning models. The classification function 𝑓𝑓: ℝ𝑛𝑛 → {1,2, … , 𝑘𝑘} maps the feature vector 𝑥𝑥𝑖𝑖 to a label 𝑦𝑦𝑖𝑖 , that corresponds to the category. Choosing an adequate model and its parameters is crucial for ensuring accuracy. 4. Information Storage. The classified information is stored in a structured format. This can be represented by a matrix 𝑀𝑀 ∈ ℝ𝑚𝑚×𝑘𝑘 , where each row corresponds to a document, and each column corresponds to a category. The element 𝑀𝑀𝑖𝑖𝑖𝑖 is filled based on the classification results of document 𝑖𝑖 for category 𝑗𝑗. This approach integrates scientific text processing methods and mathematical principles of classification to automate the process of extracting information from textual documents, ensuring efficient and accurate data processing. We will illustrate this approach with Figure 1, which depicts an algorithm with several steps, beginning with the definition of the table structure ("Step 1: Define Structure"), moving to the listing of documents for analysis ("Step 2: List Documents"), processing each document to extract information corresponding to each category ("Step 3: Process Documents"), filling the table with extracted information ("Step 4: Populate Table"), exporting the table to an Excel file ("Step 5: Export to Excel"), and providing access or a method for downloading or accessing the Excel file ("Step 6: Access Excel File"). Steps 3 and 4 indicate a focus on detail: Step 3 involves the cyclical processing of each document to extract information, and Step 4 involves the cyclical creation of new rows in the table with the extracted information. Figure 1: Document Analysis with Cyclical Processing. 4. Implementation To implement the proposed method (see section 3) for analyzing AI development strategies, NLP and machine learning methods [23] were used, specifically Python libraries such as NLTK for text preprocessing, Scikit-learn for feature extraction and classification, and Pandas for structuring and storing data in tabular format. For achieving specific goals, data were used that were collected from official state websites, governments, and international organizations (namely the full text of concepts, development strategies approved at state and international levels). Based on the analysis of AI development strategies in ten different countries and regions, a systematic table was formed that reflects the key aspects of each strategy. This approach allows for the assessment and comparison of the presence of AI development strategies, special legal regulation (both rigid and flexible approaches), the definition of specific goals at the national level, the definition of the concept of AI, as well as the presence of high- level and practical guidelines from principles to AI implementation. Therefore, to analyze this issue, experts in jurisprudence have proposed the structure in Table 2. Table 2 Structure of the results № Parameter Description 1 Country The name of the country or region for which the AI strategy was analyzed is indicated 2 AI Development Reflects whether a country or region has an officially Strategy formulated AI development strategy 3 Legally Binding Indicates the presence of legally binding regulations aimed at 4 Regulation regulating AI Non-Binding Shows whether there are non-mandatory guidelines or 5 Guidelines recommendations for regulating AI Indicates whether there is a focus on specific national goals in Specific Targets the context of AI 6 AI Definition Shows whether there is a clear definition of AI in the documents 7 High-Level Indicates the presence of high-level guidelines from Guidance international organizations 8 Practical Guidance Shows whether there are practical guidelines for the implementation of AI principles Based on the proposed approach, Table 3 with the AI results for 10 documents was formed, and simultaneously, 5 experts in jurisprudence were also asked to form a corresponding table (Table 4). To assess the effectiveness of AI in analyzing AI development strategies in different countries, a comparison was made between the results of data processed by AI (see Table 3) and the results of expert evaluations (Table 4). In the study of effectiveness, the method of direct comparison of results obtained by AI with expert ratings across a range of key parameters was applied. The accuracy of the AI was determined based on the percentage of agreement between the AI-generated data and the verified expert data. The overall effectiveness of the AI analysis was measured as the average accuracy across all categories, which allowed for an assessment of its ability to adequately understand and interpret strategic documents in the field of AI development. Table 3 AI processing results Coun AI Legally Non- Specific AI High-Level Practic try Development Binding Binding Targets Definition Guidance al Strategy Regulatio Guidelines Guidan n ce EU Yes Yes Yes Yes Yes Yes Yes Brazil Assumed Yes Assumed Assumed Yes Assumed Assumed Assum No Yes Yes Yes ed Yes Finla Yes Not Yes Yes Not Yes Yes nd specified specified India Yes Not Yes Yes Not Yes Yes specified specified Japan Yes Yes Yes Yes Yes Yes Yes USA Yes Not Yes Yes Not Yes Yes specified specified China Yes Yes Yes Yes Yes Yes Yes Ukrai Yes Not Not Not Not Not ne specified specified specified specified specifie d Queb Yes Not Yes Not Not Yes Yes ec specified specified specified Colu Yes Not Not Yes Not Yes Not mbia specified specified specified specifie d The following criteria were defined within the method for evaluation: • A full match between the results obtained by AI and expert data was scored as 1 point, indicating identical information and high accuracy of AI analysis. • A partial match, where AI used the "Assumed" marker to assess parameters that were acknowledged as correct by experts, was assigned a score of 0.9 points. This reflects a high level of consistency in results, albeit with some degree of uncertainty in interpretation. • A complete mismatch, where the information provided by AI did not correspond to expert assessments, received 0 points, indicating a complete divergence in inferences. This differentiated evaluation system provides a deeper understanding of AI's effectiveness in analyzing and interpreting complex strategic documents. Particular attention is paid to AI's ability to make adequate inferences in conditions of uncertainty, which is a key aspect in assessing its potential as an analytical tool in a wide range of applications. These results indicate a significant potential for AI in analytical research aimed at developing and improving strategies in the field of AI, and they also define directions for further enhancement of data processing and analysis algorithms. Table 4 The results of the work of 5 experts Country AI Legally Non- Specific AI High- Practical Developmen Binding Binding Targets Definition Level Guidance t Regulatio Guidelines Guidan Strategy n ce EU Yes Yes Yes Yes Yes Yes Yes Brazil Yes Not Assumed Yes Assumed Yes Assumed specified Yes Yes Yes Finland Yes Not Yes Yes Not Yes Yes specified specified India Yes Not Yes Yes Not Yes Yes specified specified Japan Yes Yes Yes Yes Yes Yes Yes USA Yes Yes Yes Yes Not Yes Yes specified China Yes Yes Yes Yes Yes Yes Yes Ukraine Yes Not Assumed Not Yes Yes Yes specified Yes specifie d Canada Yes Not Yes Not Not Yes Yes specified specifie specified d Columbi Yes Not Not Yes Not Yes Not a specified specified specified specified The analysis of Table 5, which demonstrates a comparison of results obtained by AI with expert evaluations, revealed a high overall accuracy of AI in identifying AI development strategies by countries and categories. The average weighted accuracy across categories is 0.91, which indicates the effectiveness of AI in understanding and analyzing complex data. AI showed the highest accuracy in the "Specific Targets" category with a score of 1.0 and "AI Development Strategy" with an overall accuracy of 0.99. However, in categories such as "Legally Binding Regulation", "Non-Binding Guidelines", "AI Definition", "High-Level Guidance", and "Practical Guidance", a somewhat lower accuracy is observed (ranging from 0.89 to 0.8), which may suggest the need for further improvement of AI algorithms for better identification and interpretation of these aspects. The highest accuracy by country is observed for the EU, Finland, India, Japan, China, and Quebec, where AI achieved full correspondence (1.0) with expert evaluations. However, in the case of Ukraine, the accuracy is only 0.43, which indicates significant discrepancies between AI and expert evaluations in certain categories. This could indicate a need for further refinement of AI algorithms to ensure more accurate analysis in cases with complex information or insufficient data. Thus, the implementation of the proposed approach confirms the high efficiency of using AI in the analysis of AI development strategies in various countries and regions, as reflected in Table 4. The overall AI analysis accuracy of 0.91 demonstrates its high potential as an analytical tool for assessing complex strategic documents. Particularly important is the fact that AI shows high accuracy not only in defining the general goals of development strategies but also in understanding the legal aspects of AI regulation and practical guidelines for their implementation. Despite some challenges associated with the analysis of specific categories, such as "Legally Binding Regulation" and "Practical Guidance," where accuracy was lower, the results underline the significant potential for further refinement of AI algorithms to improve analysis accuracy. Table 5 Comparison of the obtained results Country AI Legally Non- Speci AI High- Practicl Accurac Develop Binding Binding fic Definit Level Guidance y by ment Regulation Guideline Targ ion Guida country Strategy s ets nce EU 1 1 1 1 1 1 1 1 Brazil 0.9 0.9 1 1 1 0.9 1 0.96 Finland 1 1 1 1 1 1 1 1 India 1 1 1 1 1 1 1 1 Japan 1 1 1 1 1 1 1 1 USA 1 0 1 1 1 1 1 0.86 China 1 1 1 1 1 1 1 1 Ukraine 1 1 0 1 0 0 0 0.43 Quebec 1 1 1 1 1 1 1 1 Columbia 1 1 1 1 1 1 0 0.86 Accuracy 0.99 0.89 0.9 1 0.9 0.89 0.8 0.91 by category 5. Conclusions The results of the current research demonstrate the significant potential of applying AI in the process of analyzing legal documents, confirming the effectiveness of the proposed cyclical approach. The overall data processing accuracy using AI was 0.91, indicating high reliability and precision of the obtained results. Particularly impressive results were achieved in the categories "Specific Targets" and "AI Development Strategy," where the accuracy was 1.0 and 0.99, respectively, evidencing AI's ability to precisely identify key elements of AI development strategies. Based on the comparison conducted with expert evaluations (where the overall accuracy of the AI analysis was 0.91), we confirmed the high efficiency of AI in analyzing AI development strategies at the international level. The lowest accuracy by countries was recorded for Ukraine (0.43), which highlights the importance of adapting analysis approaches to the specifics of each particular legal system, in this case, the Ukrainian language. These conclusions demonstrate the significant potential for applying AI in analytical research in the legal field, as well as indicating directions for further improvement of legal document processing and analysis technologies. Ensuring high accuracy in analysis is key to enhancing the efficiency of legal processes and developing effective strategies for regulating and using AI at both national and international levels. Based on the conducted analysis, future scientific research should focus on developing improved algorithms to increase the accuracy of classification and analysis of legal documents, particularly in categories like "Legally Binding Regulation" and "Practical Guidance," where accuracy was found to be lower. Another important direction is the development of methods for the effective processing and analysis of Ukrainian legal texts, which contain a large amount of unstructured information, in order to ensure a deeper understanding of the context. References [1] B. Gates The road ahead reaches a turning point in 2024. December 19 2023. URL: https://www.gatesnotes.com/The-Year-Ahead-2024 (date of access: 21.01.2024). [2] Ethics of Artificial Intelligence. UNESCO. URL: https://www.unesco.org/en/artificial intelligence/recommendation-ethics (date of access: 21.01.2024). [3] C. Smith, T. Wuang, G. Yang, History of Artificial Intelligence, available at URL: https://courses.cs.washington.edu/courses/csep590/06au/projects/history-ai.pdf (date of access: 06.01.2024). [4] Ogwuche, Perpetua, Artificial Intelligence: The Legal Implications of Intellectual Property Rights for AI-generated Inventions (October 16, 2022). URL: https://ssrn.com/abstract=4589323 or http://dx.doi.org/10.2139/ssrn.4589323 (date of access: 12.12.2023). [5] Investopedia – What is Artificial Intelligence (AI)? URL: https://www.investopedia.com/terms/a/artificial intelligence-ai.asp (date of access: 12.12.2023 [6] I. J. Lloyd. Information Technology Law. 9th Edition. Oxford University Press, 2020, 482p. [7] F.S. De Sio, G. Mecacci, Four responsibility gaps with artificial intelligence: Why they matter and how to address them. Philosophy & Technology, 34(4), (2021). 1057-1084. doi: 10.1007/s13347-021-00450-x. [8] H. Zhong, C. Xiao, C. Tu, T. Z., Z. Liu, Maosong Sun How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence. (2020). URL : https://arxiv.org/pdf/2004.12158.pdf. [9] T. C. Bueno, C. V. Wangenheim, E. D. S, Mattos, H. C. Hoeschl, R. M. Barcia, Juris Consulto: retrieval in jurisprudence a text bases using juridical terminology. ACM. (1999). https://dx.doi.org/10.1145/323706.323789. [10] R. S. Rana, S. Singh, M. Aggarwal, M. Badoni, Unveiling the Future: Exploring AI Applications in the Indian Judicial System. IEEE. (2023). https://dx.doi.org/10.1109/ISED59382.2023.10444600. [11] W. Wyporek, Sztuczna inteligencja–wybór orzecznictwa. (2021). https://dx.doi.org/10.13166/wsge/hr-pl/mbtu5710. [12] Chucha, S. Artificial intelligence in justice: legal and psychological aspects of law enforcement. (2023). https://dx.doi.org/10.52468/2542-1514.2023.7(2).116-124. [13] Al Qatawneh, I. S., Moussa, A., Haswa, M., Jaffal, Z., &Barafi, J. Artificial Intelligence Crimes. AJIS. (2023). https://dx.doi.org/10.36941/ajis-2023-0012. [14] S. Iqbal, S.-U. Hassan, N. Aljohani, S. Alelyani, R. Nawaz, L. Bornmann, A decade of in-text citation analysis based on natural language processing and machine learning techniques: an overview of empirical studies. Scientometrics. (2020). [15] Dhala, R. R., Kumar, A.V.S.P., & Panda, S. A Comparative Study on Keyword Extraction and Generation of Synonyms in Natural Language Processing. IEEE Access. (2023). [16] M. Khanbhai, P. Anyadi, J. Symons, K. Flott, A. Darzi, E. Mayer, Applying natural language processing and machine learning technique stop a іtient experience feedback: a systematic review. BMJ Health & Care Informatics. (2021). https://dx.doi.org/10.1136/bmjhci-2020-100262 [17] Yu, H., Xiong, F., &Chen, Z. Text Classification Based on Natural Language Processing and Machine Learning in Multi Label Corpus. ACM Transactions. (2023). https://dx.doi.org/10.1145/3617831 [18] B. ShireeshaK, P. Thejas, D. S. Kumar, Document Analysis using Deep Learning Techniques. IEEE International Conference on Electrical, Computer, and Energy Technologies (ICECET). (2023). https://dx.doi.org/10.1109/ICESC57686.2023.10193742. [19] R. Gramyak, H. Lipyanina-Goncharenko, A. Sachenko, T. Lendyuk, D. Zahorodnia, Intelligent Method of a Competitive Product Choosing based on the Emotional Feedbacks Coloring. CEUR-WS 2853 (2021) 246-257. [20] K. Lipianina-Honcharenko, C. Wolff, A. Sachenko, O. Desyatnyuk, S. Sachenko, I. Kit, Intelligent information system for product promotion in internet market. Applied sciences, 13(17), (2023). 9585. doi:10.3390/app13179585. [21] I. Perova, Y. Bodyanskiy, Fast medical diagnostics using autoassociative neuro-fuzzy memory. International Journal of Computing, 16(1), (2017). 34-40. https://doi.org/10.47839/ijc.16.1.869. [22] H. Lipyanina, S. Sachenko, T. Lendyuk, A. Sachenko, Targeting Model of HEI Video Marketing based on Classification Tree. In ICTERI Workshop (2020). 487-498. [23] K. Lipianina-Honcharenko, R. Savchyshyn, A. Sachenko, A. Chaban, I. Kit, T. Lendiuk, Concept of the intelligent guide with AR support. International Journal Of Computing, (2022). 271–277. doi:10.47839/ijc.21.2.2596. [24] H. Bhatt, R. Bahuguna, R. Singh, A. Gehlot, S. V. Akram, N. Priyadarshi, B. Twala, Artificial Intelligence and robotics led technological tremors: A seismic shift towards digitizing the legal ecosystem. Applied Sciences, 12(22), (2022). 11687. [25] G. M. Csányi, R. Vági, D. Nagy, I. Üveges, J. P. Vadász, A. Megyeri, T. Orosz, Building a production-ready multi-label classifier for legal documents with digital-twin- distiller. Applied Sciences, 12(3), (2022). 1470. [26] B. Abimbola, E. de La Cal Marin, Q. Tan, Enhancing Legal Sentiment Analysis: A Convolutional Neural Network–Long Short-Term Memory Document-Level Model. Machine Learning and Knowledge Extraction, 6(2), (2024). 877-897. [27] J. L. Pach, P. Bilski, A robust binarization and text line detection in historical handwritten documents analysis. International Journal of Computing, 15(3), (2016). 154-161. https://doi.org/10.47839/ijc.15.3.848. [28] E. M.Cherrat, R. Alaoui, H. Bouzahir, Score fusion of finger vein and face for human recognition based on convolutional neural network model, International Journal of Computing, 19(1), (2020) 11-19. https://doi.org/10.47839/ijc.19.1.1688.