Abstract
Within the OpenLaws.eu project, we attempt to suggest relevant new sources of law to users of legal portals based on the documents they are focusing on at a certain moment in time, or those they have selected. In the future we attempt to do this both based on ‘objective’ features of the documents themselves and on ‘subjective’ information gathered from other users (‘crowdsourcing’). At this moment we concentrate on the first method. In Sect. 10.2 I describe how we create the web of law if it is not available in machine readable form, or extend it when that is necessary. Next, I present results of experiments using analysis of the network of references or citations to suggest these new documents. In Sect. 10.3 I describe two experiments where we mix the use of network analysis with similarity based on the comparison of the actual text of documents. One experiment is based on simple bag-of-words and normalisation, the other uses Latent Dirichlet Allocation (LDA) with added n-grams. A small formative evaluation in both experiments suggests that text similarity alone works better than network analysis alone or a combination, at least for Dutch court decisions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
These topics occur in a series of international workshops on “Network Analysis in Law (NAiL)” I have been organizing since 2013.
- 2.
- 3.
rechtspraak.nl.
- 4.
Recently one has started to add some links to cited legislation in metadata, but not all and it does not give information on where in the text the citation occurs, nor how often.
- 5.
In 2016 a new version of the Dutch legislative portal was launched that overcomes many of the problems.
- 6.
Precision gives the percentage of all references we find that is relevant or correct. Precision of 100% means all references we find are relevant or correct. Recall gives the percentage of all relevant or correct references there are, that we actually find. A recall of 100% would mean we find all relevant or correct references.
- 7.
Bibliographic conventions distinguish four levels of documents: work, expression, manifestation and item (Saur 1998).
- 8.
‘European Case Law Identifier’; see Council of the European Union conclusions on ECLI at: http://eur-lex.europa.eu/legal-content/EN/ALL/?uri=CELEX:52011XG0429(01).
- 9.
TfidfVectorizer of SciKit-learn (Pedregosa et al. 2011) was used with minimal document frequency set to 1 and maximum to.7.
- 10.
- 11.
- 12.
- 13.
Because we are interested in whether adding the bag-of-references to the similarity scores improves performance, documents that had recommendations that occurred in both sets were removed.
- 14.
MAchine Learning for LanguagE Toolkit, McCallum (2002).
References
Blei DM, Lafferty JD (2009) Visualizing topics with multi-word expressions. https://arxiv.org/pdf/0907.1013.pdf. Accessed 30 Nov 2017
Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993–1022. http://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf. Accessed 30 Nov 2017
de Maat E, Winkels R, Engers T (2006) Automated detection of reference structures in law. In: van Engers T (ed) JURIX 2006. IOS Press, Amsterdam, pp 41–50
Fowler JH, Jeon S (2008) The authority of Supreme Court precedent. Soc Netw 30(1):16–30. https://doi.org/10.1016/j.socnet.2007.05.001
Hoekstra R (2011) The MetaLex document server - legal documents as versioned linked data. In: Aroyo L et al (eds) The Semantic Web – ISWC 2011. Lecture notes in computer science, vol 7032. Springer, Berlin, pp 128–143. https://doi.org/10.1007/978-3-642-25093-4_9
Liiv I, Vedeshin A, Täks E (2007) Visualization and structure analysis of legislative acts: a case study on the law of obligations. In: ICAIL 2007 Proceedings of the 11th international conference on artificial intelligence and law. ACM Digital Library, New York, pp 189–190. https://dl.acm.org/citation.cfm?id=1276353. Accessed 30 Nov 2017
Mazzega P, Bourcier D, Boulet R (2009) The network of French legal codes. In: ICAIL 2009 Proceedings of the 12th international conference on artificial intelligence and law. ACM Digital Library, New York, pp 236–237. https://dl.acm.org/citation.cfm?id=1568271. Accessed 30 Nov 2017
McCallum AK (2002) Mallet: A machine learning for language toolkit. http://mallet.cs.umass.edu
Newman M (2010) Networks: an introduction. Oxford University Press, Oxford
Palmirani M, Brighi R, Massini M (2003) Automated extraction of normative references in legal texts. In: 9th international conference on artificial intelligence and law. ACM Digital Library, New York, pp 105–106. https://dl.acm.org/citation.cfm?id=1047815. Accessed 30 Nov 2017
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830. http://www.jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdf. Accessed 30 Nov 2017
Saur KG (1998) Functional requirements for bibliographic records: final report/IFLA Study Group on the Functional Requirements for Bibliographic Records. UBCIM publications New series vol 19, München. https://www.ifla.org/files/assets/cataloguing/frbr/frbr.pdf. Accessed 30 Nov 2017
Shani G, Gunawardana A (2011) Evaluating recommendation systems. In: Ricci F, Rokach L, Shapira B, Kantor P (eds) Recommender systems handbook. Springer, Boston, pp 257–297. https://doi.org/10.1007/978-0-387-85820-3_8
Tran OT, Le Nguyen M, Shimazu A (2013) Reference resolution in legal texts. In: Proceedings of the fourteenth international conference on artificial intelligence and law. ACM Digital Library, New York, pp 101–110. https://dl.acm.org/citation.cfm?id=2514601.2514613. Accessed 30 Nov 2017
van Opijnen M (2014) Op en in het web. Hoe de toegankelijkheid van rechterlijke uitspraken kan worden verbeterd. PhD Thesis in Dutch, University of Amsterdam
Wass C, Dini P, Eiser T, Heistracher Th, Lampoltshammer Th, Marcon G, Sageder C, Tsiavos P, Winkels RGF (2013) OpenLaws.eu. In: Proceedings of the 16th international legal informatics symposium IRIS 2013, Salzburg, February 2013, pp 209–212. https://pure.uva.nl/ws/files/2517952/167594_OPENLAWS.eu_IRIS13.pdf. Accessed 30 Nov 2017
Winkels RGF, de Ruyter J, Kroese H (2011) Determining authority of Dutch case law. In: Atkinson K (ed) JURIX 2011. IOS Press, Amsterdam, pp 103–112
Winkels RGF, Boer A, Plantevin I (2013) Creating context networks in Dutch legislation. In: Ashley K (ed) JURIX 2013. IOS Press, Amsterdam, pp 155–164
Winkels RGF, Boer A, Vredebregt B, van Someren A (2014) Towards a legal recommender system. In: Hoekstra R (ed) Legal knowledge and information systems. JURIX 2014: the twenty-seventh international conference. Volume 271 of frontiers in artificial intelligence and applications. IOS Press, Amsterdam, pp 169–178
Acknowledgements
Part of this research is co-funded by the Civil Justice Programme of the European Union in the OpenLaws.eu project under grant JUST/2013/JCIV/AG/4562. I would like to thank my students: Erwin van den Berg, Bart Vredebregt and Wolf Vos who performed the experiments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Winkels, R. (2019). Exploiting the Web of Law. In: Boulet, R., Lajaunie, C., Mazzega, P. (eds) Law, Public Policies and Complex Systems: Networks in Action. Law, Governance and Technology Series, vol 42. Springer, Cham. https://doi.org/10.1007/978-3-030-11506-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-11506-7_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-11505-0
Online ISBN: 978-3-030-11506-7
eBook Packages: Law and CriminologyLaw and Criminology (R0)