Towards an Integrated Database of International Economic Law (IDIEL) Disputes for Text-as-data Analysis
This paper introduces an infrastructure for the analysis of legal metadata and textual data on international investment and trade disputes. The developed database architecture consists of three main components: (1) a WebCrawler of two key web sites for international economic law dispute information; (2) a document analyzer to transform PDFs into text files, identifying structure and footnotes within document, finding references to other disputes and storing texts as XML; and (3) multiple user interfaces to allow different user types to access the data. The architecture allows users to launch metadata queries and/or to investigate textual corpora. It therefore provides a versatile new framework for international economic law research from various angles and disciplines.
Inhaltsverzeichnis
- 1. Introduction
- 2. Background
- 3. Architecture
- 3.1. Data Storage
- 3.2. Document and Metadata Retrieval
- 3.3. Document Analysis
- 3.4. User Interface
- 4. Data Model
- 5. Methodology
- 5.1. PDF to XML Conversion
- 5.2. XML Conversion and Handling
- 5.3. Multi-Part Document Handling
- 5.4. Cleaning Up
- 5.5. Structure Analysis
- 5.6. Reference Recognition
- 5.6.1. Trade Law Disputes
- 5.6.2. Investment Law Disputes
- 6. Examples
- 7. Issues
- 8. Evaluation
- 9. Conclusion and Future Work
- 10. Appendix
Loggen Sie sich bitte ein, um den ganzen Text zu lesen.
There are no comments yet
Ihr Kommentar zu diesem Beitrag
AbonnentInnen dieser Zeitschrift können sich an der Diskussion beteiligen. Bitte loggen Sie sich ein, um Kommentare verfassen zu können.
No comments