14 December 2022, 10-13 hours, HYBRID; Link on request from the JURIX Organisers

held in conjunction with
14-16 December 2022, Saabruecken, Germany, Saarland University

Workshop Organizers: Stefan Eder, Erich Schweighofer


Session 1 – 10:00-11:00 hours; chair:  Stefan Eder, Erich Schweighofer
    • Introduction to the topic of Legal Data Analysis by the Chairs; discussion of major concepts and research questions (getting an update to the state of the art)
    • Summary of related work, in particular: Kevin Ashley, Legal Data Analytics (2018), Erich Schweighofer, Legal Knowledge Representation (1999) + updates, e.g. 9-Level Legal Knowledge Representation
    • Bernhard Waltl, New developments in data analysis to be interesting in the legal environment
Session 2 – 11:00-13:00 hours: chair: Stefan Eder

Roundtable: Experts on legal data analysis shortly present approaches, to  be discussed by the panel and the audience

  • Christian Sageder, CYBLY, Salzburg/Wien: Options for storing legal texts, optimised for both humans and machines. Advantages and disadvantages of the various common formats
  • Erich Schweighofer, Uni Wien, Arbeitsgruppe Rechtsinformatik: Thoughts about an Advanced Law Identifier (A-LawI), based on the CELEX number and the RIS number
  • Florina Piroi, Tobias Funk, Clemens Furtlehner, Johannes Braun: First results of two indexing and classifying systems: IRI§ Text Corpora (2000-2022) and International Law Exams (2020)
  • Michael Araszkiewicz, The potential of logical formaliation for text analysis
  • Open forum for participants to present its projects and ideas
  • Discussion and assessment on the way to move on
Session 3 –  14:00 – 15:00 hours; chair:  Stefan Eder, Erich Schweighofer
Zoom Space University of Vienna (link on request)

Discussion about possible research projects and co-operation between participants; platform



The 7th Workshop on Legal Data Analysis (LDA22) of the Central European Institute of Legal Informatics (CEILI) will be held in conjunction with JURIX2022, on Wednesday December 16th, 2022, HYBRID. It is a continuation of the successful LDA workshops in 2015-2021.

It intends to focus on representation, analysis and reasoning with legal data in information systems from a lawyer’s and citizen’s perspective; trying to get support in mastering big data in law but also respecting privacy issues.

The pervasive use of information systems has led to tremendous success in enterprises and businesses. With a user-centric design, information systems (IS) have proven their value in today’s companies on several occasions. Most recent developments have unveiled unexpected possibilities in overcoming the retrieval constraints of access to legal knowledge. In law, the need arises for both legal databases as well as huge data volumes of cases. Market solutions are already available.

However, theoretical work and practical reflection for time-, data-, and knowledge-intensive tasks, which most of the tasks in legal science and legal practice are still highly relevant. Pre-defined formal models of legal knowledge and semantic documents allow semantics of textual and structural information with tools of Natural Language Processing, Named Entity Recognition, Network Analysis, Information Retrieval and additional analysis and measurements. This workshop particularly encourages submissions describing concrete user problems, needs and concerns in the context of legal data and legal analysis and theoretical reflection.

This workshop is intended to be a forum for discussion of research ideas, questions and developments addressing all kind of concrete user support in processes related to the representation, analysis and reasoning on legal information and data analysis.

Participation is most welcome on all topics relevant to these research domains, including:

  • Reasoning with legal information and legislative texts (including contracts and patents)
  • Modeling and design of legal information, legislative texts, electronic contracts and SLAs
  • Usage of ontologies in information systems to support representation, analysis and reasoning on legal information
  • Analysis of the network like structure of legal systems and legislations
  • Forecast and prediction models on legal data
  • Big Data analysis of textual information In large legal text corpora
  • Access to Data and Open Data Initiatives
  • User stories and use cases of legal analysis in combination with IS
  • Predictive Coding
  • Natural Language Processing in IS
  • Multi-lingual aspects of NLP in the legal domain
  • Interoperability of logic frameworks and natural language processing
  • Drawbacks and limitations of logic frameworks, natural language processing, usage of ontologies in IS, etc.
  • Measurements, such as quantitative linguistics, and correlations on legal data
  • Information retrieval in IS, including optimization, reformulation, refinement and expansion of queries and facets
  • Semantic relations in electronic files
  • Societal impact of emerging IS technology in the legal domain
  • Argumentation mining
  • Legal interpretation modelling (including judicial interpretation and doctrinal interpretation)
  • Technical solutions to privacy and big data issues

We invite researchers to submit their original papers (drafts 4-10 pages, final papers: 8 pages, 2400 words) on these themes. In case of acceptance, the paper will be included in the workshop materials and later extended versions should be published in Jusletter IT (http://www.jusletter-it.eu).

Format & audience

1/2 day workshop with paper presentations and 1 panel discussion

6 papers, 5 panelists, about 15-20 particpants