Use Case Scenarios on Legal Text Mining

In May 2004 the European Union was enlarged by ten new member states, eight of these were countries from the former Communist bloc. Between May 2004 and May 2006 the citizens of so-called EU8 countries (Czech Republic, Estonia, Hungary, Latvia, Lithuania, Poland, Slovak Republic and Slovenia) enjoyed full worker mobility in only three ‘old’ EU member states, the Republic of Ireland, Sweden and the United Kingdom. Following EU enlargement, migrant workers from EU8 countries as well as their dependants have been arriving in the United Kingdom. In December 2007 almost 800,000 workers from EU8 countries were registered on the government's worker registration scheme. This article is concerned with the transnational practices of migrants from EU8 countries who have arrived in the UK following EU enlargement, in particular with everyday transnational practices that involve the use of a variety of media. The experiences of transnational migrants involve connections between former and new (sometimes temporary) homelands. The role of media, in particular satellite television, has been studied in a transnational context. However, satellite broadcasting has not been embraced by migrants from EU8 countries to any extent, rather they rely on a range of media and practices that enable them to be connected to two or more national contexts. Migrants interviewed for this research have proved to be avid and highly skilled users of digital media in particular, they access newspapers, magazines and films online, use Skype to make calls, post photographs on social networking sites and even check online images of their home towns in Eastern Europe on a daily basis. The article explores the implications of these transnational practices in relation to migrants' identities and belonging as well as political participation. The data analyzed in the article was collected in in-depth qualitative interviews with 20 recently (post-May 2004) arrived migrants from EU8 countries in London, Edinburgh and Newcastle. The interviews were conducted in winter 2006 and summer 2007.

Retrieval-augmented generation (RAG) has proven highly effective in improving large language models (LLMs) across various domains. However, there is no benchmark specifically designed to assess the effectiveness of RAG in the legal domain, which restricts progress in this area. To fill this gap, we propose LexRAG, the first benchmark to evaluate RAG systems for multi-turn legal consultations. LexRAG consists of 1,013 multi-turn dialogue samples and 17,228 candidate legal articles. Each sample is annotated by legal experts and consists of five rounds of progressive questioning. LexRAG includes two key tasks: (1) Conversational knowledge retrieval, requiring accurate retrieval of relevant legal articles based on multi-turn context. (2) Response generation, focusing on producing legally sound answers. To ensure reliable reproducibility, we develop LexiT, a legal RAG toolkit that provides a comprehensive implementation of RAG system components tailored for the legal domain. Additionally, we introduce an LLM-as-a-judge evaluation pipeline to enable detailed and effective assessment. Through experimental analysis of various LLMs and retrieval methods, we reveal the key limitations of existing RAG systems in handling legal consultation conversations. LexRAG establishes a new benchmark for the practical application of RAG systems in the legal domain, with its code and data available at https://github.com/CSHaitao/LexRAG.

An empirical analysis of consumer-unfriendly E-commerce terms of service agreements: Implications for customer satisfaction and business survival

Abstract: The RAG-Based Legal Assistant Chatbot is a cutting-edge AI-powered solution designed to streamline legal information retrieval and document analysis. By leveraging Retrieval-Augmented Generation (RAG) and integrating technologies such as LangChain and FAISS (Facebook AI Similarity Search), the chatbot processes and indexes large volumes of legal documents, delivering precise and contextually relevant insights to user queries. This project addresses the challenge of navigating extensive legal literature by transforming legal PDFs into searchable embeddings stored in FAISS. Users interact with the system through a conversational interface built with Streamlit, which maintains query context to ensure accurate and accessible responses for legal professionals and non-specialists alike.The system’s backend infrastructure is implemented in Python, utilizing LangChain for efficient language model operations and FAISS for semantic search. Key functionalities include document ingestion, intelligent retrieval, and conversational interaction. The design prioritizes scalability and adaptability, enabling future integrations with diverse legal knowledge bases and supporting additional languages or jurisdictions.The chatbot’s performance has been validated through extensive testing, showcasing high retrieval precision and low response times. These features significantly enhance productivity by automating time-consuming tasks such as document search and legal analysis, allowing users to focus on critical decision-making.This project highlights the transformative potential of AI in the legal domain, bridging the gap between complex legal information and user accessibility. Future developments will aim to enhance the system's natural language processing capabilities, incorporate real-time data updates, and integrate advanced security measures to safeguard sensitive legal information. In conclusion, the RAG-Based Legal Assistant Chatbot is an intelligent and robust tool that simplifies legal information access, demonstrating how AI can revolutionize traditional industries through precision, scalability, and innovation

It is determined that the process of cooperation within the framework of the European Union has increased the need for identification and exchange of legal information coming from regional and national authorities at the European level. This need is partially met by digitally accessible legal information and the widespread use of the Internet. However, the exchange of legal information is largely limited by the differences that exist in different national legal systems, as well as the differences in their technical systems used to store and display the law on their respective websites. This hinders interaction between the information systems of national and European institutions, despite the increase in the availability of documents in electronic format. At the same time, the interconnection of national and international legal information from various sources and their presentation in the form of linked data of legal knowledge will undoubtedly improve the process of searching for legal information, expanding the possibilities of inquiries that are not currently possible. Moreover, in an increasingly digital society, where the number of cross-border civil and criminal proceedings is rapidly increasing, and given the complex diversity of different legal systems in the EU Member States, the simplification and facilitation of cross-border judicial cooperation is essential to ensure effective access of citizens and businesses to justice. At the same time, the system of identification and metadata should be well known to citizens and specialists in the field of law. In addition, to increase the chances of finding case law that is supported by an identifier and metadata, these court decisions should be searchable - by identifier and a minimal set of metadata - through a common interface. The exchange of digital evidence in the EU is also an important aspect. Currently, countries cooperate using private international law in cross-border criminal cases and exchange digital evidence based on these tools. The choice of tool depends on the countries involved and the type of information required.

Social studies on the communication problems between the state, society, and citizens are particularly relevant in the modern world. This article is dedicated to a way of enhancing the quality of communication between lawmakers and society known as "normative promotion." The author proposes to understand normative promotion as the activities of a regulator (lawmaker) aimed at forming a unified communicative legal space by informing citizens (the addressees of legal regulation in general) about the legal regulation being introduced, explaining the content of new legal acts or legal norms with the aim of fostering a conscious attitude towards these norms and a positive perception of legal regulation. Ignoring the systematic work of the state in the field of normative promotion can lead to both a decrease in the effectiveness of regulation in general and the emergence of social tension and conflicts within society in particular. It is advisable to consider the practices of normative promotion from the perspective of the communicative theory of law, which serves as the methodological basis for the research, namely, in the context of the dialogue between the legislator and society, where the main role is played not by the regulator as the author of the message, but by the addressee, that is, society or citizens. By examining the connection between normative promotion and other methods of enhancing the quality of lawmaking communication, the author addresses the question of whether the practice of normative promotion has practical significance for legal expertise as an activity aimed at assessing the quality of legal acts. As a result, the author concludes that organizational means, such as deliberative practices, legal expertise, and normative promotion, can serve to improve communication. The article also argues that the improvement of communication should be ensured by legal means, as all the aforementioned practices are poorly or not at all legally supported. In particular, normative promotion, as an activity related to shaping public opinion, is associated with risks of abuses and political manipulations, thus requiring strict legal regulation. Furthermore, it is justified that technical means, primarily information technologies, should also contribute to improving communication between lawmakers and society, which can be applied in parliamentary activities, particularly in ensuring dialogue between parliamentarians and citizens, normative crowdsourcing, legal information dissemination, and legal (including public) expertise of draft legal acts.

The purpose of the article. Sustainability development issues, particularly Environmental, Social, and Governance (ESG) factors, are becoming increasingly relevant in corporate reporting, driven by rising environmental awareness and regulatory requirements. The aim of the study is the evaluation of ESG disclosures of selected Polish banks. The aim of the paper fills a gap in the Polish academic literature in economics and finance by analyzing the volume and size of non-financial ESG disclosures through computer text mining techniques. Methodology. This study applies text mining techniques to evaluate the ESG volume and size from 107 financial reports issued by Polish banks between 2006 and 2023. For this purpose, selected tools for computer-based analysis of textual data (text mining) are used. The primary methods include the emotional attitude (sentiment), analysis of the number of words regarding ESG, and analysis of the readability of ESG volume and size contained in company reports. Results of the research. The study reveals that ESG excerpts are more neutral or less optimistic compared to integrated reports, which tend to have a more positive tone. Additionally, sustainability disclosures are written in a complex language, and the volume of these reports has been increasing over time, likely due to new regulations and growing awareness of sustainability issues. The study focuses on Polish banks but suggests expanding future research to other sectors.

The digitalization of the economy as a whole, and of manufacturing in particular, is one of the top-priority tasks that governments, business and society face. Central in this process is the implementation of Industry 4.0, which leading and international organizations expect to become a driver of economic development. Therefore, the objective of the study is to define the impact of digitalization on pace of industrial development at the national level. EU member states have been selected as the subject of the study. Comparing countries within the EU's single economic space is the most consistent for several reasons. On the one hand, all of these countries operate under similar institutional conditions, and on the other – the single market facilitates the free movement of capital and labor to the utmost. Also, the vast majority of EU member states are members of the monetary union and use the single currency – euro. Correlation analysis has been chosen as the main method to study the conformity of industrial production dynamics with the processes of digitalization. The results of the study in the most generalized form prove the inconsistency between high levels of digitalization and high rates of industrial production. EU member states, the leaders in terms of digitalization, demonstrate lower rates of industrial production growth than those countries that have lower levels of digital development. The hypothesis on positive impact of high levels of digitalization on industrial production at the national level has not been confirmed. However, it is not advisable to consider the results of the study as a sufficient basis for the final refutation of this hypothesis. One possible explanation for the relatively slower pace of industrial production growth in countries with high levels of digitalization is the following. The high level of industrial development causes the high level of digitalization, but at the same time leads to the "trap of high level of production", when each successive percentage, having a high base of comparison, becomes increasingly difficult. A typical example is the comparison between the Netherlands and Romania. Romania ranks 28th (last) in the average digitization rate across all EU countries and 1st in terms of average industry volume growth. At the same time, the Netherlands ranks 28th in terms of average growth of the industry volume index and 3rd in terms of digitalization. Thus, it can be argued that at the moment, digitalization (digital capital) does not have a decisive influence on the relative (when comparing between countries) growth rates of industrial production.

Overarching objective of the EU biodiversity strategy for 2030 is recovering biodiversity by strengthening the protection and restoration of nature. Key elements are the creation of protected areas on at least 30% of Europe's land and sea area, including stronger protective measures for forests. However, any implementation of dedicated measures will reduce roundwood production in EU member states. It is to be expected that parts of this reduced roundwood production will be compensated by increasing roundwood production in non-EU countries. There is a fundamental risk of biodiversity losses in non-EU countries accompanying such leakage of roundwood production. From a global perspective, such biodiversity losses must be opposed to biodiversity gains in EU countries. The presented study provides a first assessment of possible leakage effects and rep-resents the state of work as of September 2020. At first, the presented study provides an estimate of the decline in roundwood production in EU member states as a result of implementing partial or full production restrictions in forests. In a second step, implications of reduced roundwood production within EU-27 on global wood markets are assessed. Finally, leakage of roundwood production to non-EU countries is evaluated using indicators related to governance, sustainable forest management, biodiversity, forest condition, deforestation pressure and socio-economic aspects. In order to estimate the reduction in roundwood production in EU countries firstly three single implementation measures are assessed and then consolidated for Germany: (i) 10 % share of forest area set-aside, (ii) non-utilization of 'old-growth forests' and (iii) 30 % share of protected forest areas under Habitats Directive management requirements. As a result, the potential roundwood production in Germany declines on average within the period examined (2018 - 2052) by 23.96 million m³/a to 52.77 million m³/a or to 69 %. In the following calculations, this reduction share is assigned to all EU-27 countries. [...]

Theoretical background: Telemedicine has become a critical component of modern healthcare, offering the potential to improve patient outcomes, streamline clinical workflow, and facilitate more informed decision-making. Its implementation in healthcare systems offers the opportunity to leverage technology to improve access, efficiency, and quality of care. Purpose of the article: This study aims to investigate the implementation of telemedicine in the Polish healthcare system and assess its adoption in comparison with other EU countries. It also aims to assess the impact of the rate of adoption of teleconsultations as a percentage of all consultations in Poland on the quality and accessibility of healthcare in comparison with other EU member states. Research methods: This research used a literature-based approach, analyzing existing scientific articles, government reports and OECD data to understand the current state of telemedicine in Poland and EU countries. Data on the implementation rate of medical teleconsultations as a percentage of all consultations were collected from national healthcare databases and Eurostat. Main findings: The study highlights the urgent need to prioritize telemedicine in Poland to enhance healthcare efficiency. Poland’s teleconsultation rate (25%) and digitized health records (41%) lag behind leading EU nations such as Denmark, Germany, and the Netherlands, which have higher telemedicine adoption and fully digitized records. The low adoption rate in Poland contributes to inefficiencies, administrative burdens, and healthcare disparities, especially in rural areas. Countries with advanced telemedicine systems demonstrate improved patient outcomes, reduced hospital congestion, and optimized resource allocation. Strategic measures, including infrastructure development, policy reforms, and digital education, are essential for Poland’s healthcare modernization.

The necessity and relevance of the study of the experience of formation and implementation of anti-corruption policy in the EU member states in order to implement it in Ukraine, due to its European integration vector of development is substantiated. The essence and causes of corruption depending on the spheres of society, as well as the characteristics of corruption in Ukraine and its impact on the economic and social parameters of the country, resulting in lower living standards. The existing models of perception of corruption in the world and the main strategies of anti-corruption activity are described. It is proved that the choice of strategy and model of anti-corruption activities in each country depends on many factors, and Ukraine's European integration course requires harmonization of national anti-corruption legislation with EU standards. The main causes of corruption in EU member states and features of anti-corruption policy of some European countries are analyzed. It has been shown that corruption is more or less common to almost all EU countries, however, common to all countries in terms of formation and implementation of anti-corruption policy is that it aims to minimize opportunities for corruption offenses. It is established that the basis of the anti-corruption policy of the Scandinavian EU member states is the concept of public administration "Good Governance", which combines institutions, processes and mechanisms through which citizens express their interests and exercise legal rights. It was found that EU countries do not pursue a common anti-corruption policy, and each country develops its own anti-corruption infrastructure, which aims to minimize opportunities for corruption offenses. It is proved that the insufficient effectiveness of the mechanisms of the state anti-corruption policy makes it impossible to carry out structural reforms on the way to full membership of Ukraine in the EU. Priority areas for further formation and implementation of anti-corruption policy in Ukraine have been identified, taking into account European integration aspirations and existing international standards.

Sustainable economic growth is considered a fundamental problem due to the effects that can be felt on the society as a whole, along with the phenomenon of banking integration that can influence the development of a country’s economy. This research aims to investigate the impact of banking market integration on sustainable economic growth in EU countries, especially in the context of financial integration, a good consolidation of the banking market is needed. We also identified the main factors by which the development of the banking market influences economic growth. The analysis was carried out for the period 2004–2018 in EU countries as a sample. According to the results obtained, we can say that European banking integration has a positive influence and has many benefits on the growth and sustainable development of the economy. The main factors by which banking integration significantly and positively favors economic growth are convergence of asset returns, convergence of interest rates, cross-border lending to the non-banking sector, foreign assets and foreign liabilities), the ratio of international banking activities, the ratio between assets and GDP, and the net interest margin (only when maintaining a low level) with some differences between the pre-crisis and the post-crisis period, the countries in the Euro Zone outside the euro, and the new EU member states and the old EU member states.

In recent years, Brazil’s federal judicial system has embraced digitalization, making a large amount of legal process information available to citizens and legal experts. Despite the advances, a significant portion of the data produced and stored in legal systems presents itself in the form of natural language text, including numerous petitions and legal decisions. This creates barriers for automated querying and analysis of legal process data, especially considering the importance of the content of legal decisions in these tasks. In this paper, we report on an automated semantic annotation pipeline for judicial decision texts obtained from the official National Uniformization Panel (TNU) jurisprudence website. NLP models are trained in a few-shot learning context with a training set annotated by legal experts. The semantic annotation approach is evaluated using precision and recall. The results of the semantic annotation are produced into RDF-based nanopublications aligned with a reference domain ontology. The annotations are accompanied with provenance information including identification of the machine learning model used.

Sustainability has become a central concern globally, and efforts to enhance it are being made across various fields. In line with this trend, corporate sustainability reports have become more widely published. These reports provide both financial and non-financial information on a company’s sustainability. In this context, this study aims to, first, analyze the key keywords contained in CEO messages. Second, it examines whether the keywords emphasized by CEOs change in response to shifts in corporate risk under economic uncertainty. Finally, it identifies how the categories of words included in these messages are classified. To address these research questions, text analysis was selected as the methodology. Specifically, a qualitative research approach using text mining and CONCOR analysis was conducted on the text from sustainability report. According to the Term Frequency and Term Frequency-Inverse Document Frequency analyses, the most frequently occurring keywords were ESG, Sustainable, Society, Stakeholders, Growth, Environment, Effort, and Future. Centrality analysis identified the following keywords as having high centrality: Sustainable, ESG, Society, Environment, Growth, Effort, and Stakeholders. Finally, CONCOR analysis revealed four clusters: Eco-friendly Energy, ESG Management, Global Crisis, and Technological Competitiveness. This study is significant in that it analyzes the major keywords and their changes within unstructured text data using text mining and CONCOR analysis, and it suggests the possibility of future quantitative analysis of non-financial information using these keywords.

Purpose: We developed a multiyear database of sexual orientation- and gender identity-related U.S. state laws to advance sexual and gender minority (SGM) health research and practice and assessed variability in U.S. state laws from 1996 through 2016 across all U.S. states and D.C. Methods: Between 2014 and 2016, a multidisciplinary group of SGM health researchers and legal experts used secondary and primary legal sources and policy surveillance methods to systematically develop a state-level legal database of 30 sexual orientation- and gender identity-related U.S. state laws in 9 legal domains from 1996 through 2016. We calculated descriptive statistics and created maps to observe the distribution of these laws over both time and space. Results: Although progress has occurred in some domains, such as same-sex marriage, adoption, and employment discrimination, significant challenges to SGM rights remain, especially with regard to HIV criminalization, transgender rights, and discrimination in health care settings. Further, notable variation exists in the presence of protective lesbian, gay, bisexual, transgender, queer (LGBTQ) state laws across U.S. states and D.C. Conclusion: Efforts to repeal harmful U.S. state laws are needed, as are new laws, policies, regulations, practices, and norms that advance social justice and health equity for all SGM people.