Law and Tech Research

Description: The LAWNOTATION project aims to develop an infrastructure that allows researchers to making legal data and annotation schemes (current and future) accessible for annotation and analysis purposes, to develop an annotation platform for analyzing the linguistic and legal characteristics of legal documents, and to build a user-friendly interface.

A team of developers will work closely together with researchers on the improved access to legal materials. LAWNOTATION is an initiative of the Digital Legal Studies cluster in the Sectorplan Social Sciences and Humanities (SSH) - Rechtsgeleerdheid and other Dutch universities that are collaboratively working on questions related to the digitalisation of law. The research is made possible by the Platform Digitale Infrastructuur SSH

Researchers: prof. Gijs van Dijck (Maastricht University), Shashank Chakravarthy (BISS), prof. Martijn Wieling, prof. Michel Vols (Groningen University), prof. Tom van Engers, prof. Guiseppe Dari-Mattiacci, dr. Balasz Bodó (University of Amsterdam), prof. Andre Janssen, prof. Pietro Ortolani, dr. Pieter Wolters (Radboud University), prof. Floris Bex (Tilburg University / Utrecht University), Robert van Doesburg (TNO / University of Amsterdam).

Status: Ongoing (2022 – 2024)

More information: Code and documentation will be made available on the website (under construction).

Description: Flying Forward 2020 (FF2020) is a three-year collaborative research project that will develop a new Urban Air Mobility (UAM) ecosystem aligned with the Digital Government Transformation (DGT) of European countries, which focuses on incorporating UAM within the geospatial data infrastructure of cities. Building and incorporating all related data from UAM infrastructures and operations within the digital infrastructure of cities will allow helping society to fly forward in a safe, secure and effective way.

The Lab is responsible for the work package that focuses on transforming legislative provisions into machine-interpretable code. Flying Forward 2020 is funded by the European Union H2020 Research and Innovation Programme under Grant Agreement No. 101006828.

Researchers: Gijs van Dijck, Rohan Nanda, Daniel On, Shashank Chakravarthy, Kevin Jacobs, Rico Mockel (DKE)

Status: Ongoing (2020-2023)

More information: https://www.ff2020.eu/

Description: Traditionally, court decisions are manually read and analyzed in legal education and legal research. However, network analysis based on court citations have shown the potential to answer questions such as: What are the landmark cases in a corpus of decisions?, Which clusters of decisions can be distinguished, and Do certain courts cite different decisions? This project aims at bridging the gap between available computer science techniques for law, and the non-technical legal community. It will provide legal researchers and law students a software platform that visualizes large sets of court decisions as a network, where nodes represent cases and edges represent citations. Users can navigate through the corpus, spot clusters of cases, and access the full case documentation of any selected case in the network.

This project will provide legal researchers, students, and practitioners an accessible gateway to available technologies applicable to their studies, research or work. This project is funded by a Comenius Teaching Fellows 2019 grant and by a Surf Open Leermaterialen (Web of Law) 2020 grant.

Researchers: Gijs van Dijck, Kody Moodley, Marcel Schaper, Michel Dumontier, Shashank Chakravarthy, Maxine Hanrieder, Bogdan Covrig, Turgay Saba, Pedro V. Hernández Serrano.

Status: Ongoing

More information: The link to the application, documentation, manuals, and the code can be found on Maastrichtlawtech.github

Description: This project develops a textbook on legal network analysis. The book provides for an introduction (theoretical and practical) on network analysis for legal researchers and practitioners with limited or no technical expertise.

Researchers: Gustavo Arosemena, Gijs van Dijck, Roland Moerland, Maxine Hanrieder.

Status: Ongoing (2022).

More information: To be published.

Description: Illegal markets and their connections are difficult to uncover on the Darknet. Additionally, the anonymity on the Darknet allows vendors to stay undetected by using multiple vendor aliases or frequently migrating between different markets. VendorLink proposes a Transformer-based approach to identify relationships between illegal markets and their vendors. VendorLink examines writing patterns to link unique vendor accounts across the advertisements on seven public Darknet markets.

Researchers: Vageesh Saxena, Jerry Spanakis (supervisor), Gijs van Dijck (supervisor).

Status: Ongoing (2020 – 2024).

More information: To be published.

Description: Statutory article retrieval is the task of automatically retrieving statutory provisions relevant to a legal question. While recent advances in natural language processing have sparked considerable interest in many legal tasks, statutory article retrieval remains primarily untouched due to the scarcity of large-scale and high-quality annotated datasets. 

This project addresses this bottleneck by constructing the Belgian Statutory Article Retrieval  Dataset (BSARD), which consists of 100+ French native legal questions labeled by experienced legal experts with relevant articles from a corpus of 22,600+ Belgian statutory provisions. BSARD is used to develop several retrieval approaches. The aim is to test to what extent machines can identify relevant legal provisions given a certain legal question.

Researchers: Antoine Louis, Jerry Spanakis (supervisor), Gijs van Dijck (supervisor).

Status: Ongoing (2020 – 2024).

More information: Github.com

Description: Article 82 GDPR has direct effect and thus offers a direct legal remedy. However, the concept of damages is only very broadly defined. This project analyzes whether and under which circumstances non-material damages should be awarded for psychological harms, such as anxiety and distress.

Researchers: Stephan Mulders, Aurelia Tamo-Larrieux (supervisor), Gijs van Dijck (supervisor).

Status: Ongoing (2020 – 2024).

More information: To be published.

Description: This highly interdisciplinary research project is situated at the intersection of law, linguistics and computer science. It aims to explore how automation and computational tools can assist in the detection of legal (non-)compliance in the transposition of EU directives, specifically by applying comparative computational linguistics to the legislative texts of directives and their corresponding transpositions. The multilingual analysis extends to Member States that have Dutch, English, French, German or Spanish as an official legislative language. The legal area of focus is on consumer protection. The results of this project will provide empirical, quantitative evidence for observations commonly made in legal and legal-linguistic literature.

Researchers: Hellen van der Kroef, Rohan Nanda (supervisor), Daniel On (supervisor), Gijs van Dijck (supervisor).

Status: Ongoing (2021 – 2025).

More information: To be published.

Description: RECOGNISE aims at developing an interdisciplinary training curriculum on legal reasoning and cognitive science, filling a gap in legal higher education. It is a strategic partnership of six European universities for higher education sponsored by the ERASMUS+ Programme. The project will provide the interested learners (legal researchers, law students, legal practitioners, and beyond) with introductory and advanced materials on topics including heuristics and biases in adjudication, cognitive structure of legal concepts, and defeasible reasoning in law. Materials will be provided in the form of an online handbook, video lectures, summer schools, and other online and on-campus activities. This project is funded by the ERASMUS+ program.

Researchers: Antonia Waltermann, Jaap Hage, Rūta Liepiņa, Kody Moodley

Status: Ongoing (2020 - 2023)

More information: Recognise.academy

Description: We provide our private information that might be profitably used by suppliers of free digital content. Since these transactions affect consumers and their personal data, they fall within the scope of two fields of the European Union (EU) law – data protection and consumer law. Behavioral research has demonstrated that consumers tend to overestimate the benefits and underestimate non-monetary costs of free digital content in the form of exposure to advertisements. Yet, it is still unknown how free offers influence consumer decisions that are relevant from a legal perspective, i.e., decisions that involve consumer rights and privacy. FreeDigital addresses this knowledge gap. The project is funded by the Marie Skłodowska-Curie Actions which provide research fellowships within the European Commission Horizon 2020 framework.

Researchers: Monika Leszczyńska.

Status: Ongoing (2019 - 2022).

More information: Empiricalcontracts.com

Description: One of the most typical applications of algorithms and big data by online sellers, is the use of profiling to personalise prices, advertisements, shopping experiences etc. to manipulate consumers and optimise sellers’ turnover. These manipulative techniques often cross the line of the prohibition of unfair commercial practices and infringe the rights of consumers. This project explores whether automated generation of persona (based on big data) can be used in combination with a mystery shopping bot, to help them in detecting these infringement by online sellers in a more efficient, less time-consuming way. The project is funded by Idea Generator (NWA-IDG) (grant number NWA.118.192.297).

Researchers: Caroline Cauffman, Pedro V. Serrano Hernandez.

Status: Completed (2020 - 2021).

More information: NWO.nl

Description: Inspired by the recent social movement of #MeToo, this project aims to develop a chatbot to assist survivors of sexual harassment cases. The motivation behind this work is twofold: properly assist survivors of such events by directing them to appropriate institutions that can offer them help and increase the incident documentation so as to gather more data about harassment cases which are currently under reported. This project breaks down the problem into three data science/machine learning components: harassment type identification (treated as a classification problem), spatio-temporal information extraction (treated as Named Entity Recognition problem) and dialogue with the users (treated as a slot-filling based chatbot). The results indicate a success rate of more than 98% for the identification of a harassment-or-not case and around 80% for the specific type harassment identification. Locations and dates are identified with more than 90% accuracy and time occurrences prove more challenging with almost 80%. The initial validation of the chatbot shows great potential for the further development and deployment of such a beneficial for the whole society tool.

Researchers: Tobias Bauer, Emre Devrim, Misha Glazunov, William Lopez Jaramillo, Balaganesh Mohan & Gerasimos Spanakis

Status: Completed (2020)

More information: Link.springer.com

Description: Financial crimes committed across borders by companies and other entities in the EU are becoming increasingly difficult to detect and prevent. This project builds a Knowledge Graph to help tell a connected story about EU corporate mobility from disconnected data sources. This project is funded by a NWO Idea Generator (NWA-IDG) (grant number NWA.1228.192.285).

Researchers: Kody Moodley, Marcus Meyer-Erdmann, Rūta Liepiņa, Pedro V. Hernández Serrano.

Status: Completed (2020 - 2021).

More information: Eu-corporate-mobility.org

Judicial cooperation in criminal matters and mutual recognition models in the EU still need to be fully harmonized across Member States. There is a gap between EU law and national law, as standards of protection may not have the same substantial meaning in EU law and in domestic jurisdictions. Other factors also hamper the effectiveness of mutual recognition instruments, such as diverging legal traditions, linguistic barriers, or scarce access to other States’ domestic case-law. Thanks to a multidisciplinary research team in criminal law, IT and legal informatics, FACILEX aims to fill this gap by tailoring legal knowledge to achieve accurate decision-making. It provides a multilevel online platform grounded on a comprehensive comparative legal analysis, focusing on the implementation of EU mutual recognition instruments in different Member States.

Our Contribution

Our team will develop multilingual natural language processing tools and resources for the harmonization of the EU mutual recognition instruments with the National legislation and Case-law. We will also be involved in the legal research and analysis of the EU Cooperation Mechanisms with the aim of delivering a national report for the Netherlands. The scientific team for FACILEX at Maastricht University consists of Rohan Nanda and Gijs van Dijck.