Abstract
The perspective of online dispute resolution (ODR) is to develop an online electronic system aimed at solving out-of-court disputes. Among ODR schemes, eMediation is becoming an important tool for encouraging the positive settlement of an agreement among litigants. The main motivation underlying the adoption of eMediation is the time/cost reduction for the resolution of disputes compared to the ordinary justice system. In the context of eMediation, a fundamental requirement that an ODR system should meet relates to both litigants and mediators, i.e. to enable an informed negotiation by informing the parties about the rights and duties related to the case. In order to match this requirement, we propose an information retrieval system able to retrieve relevant court decisions with respect to the disputant case description. The proposed system combines machine learning and natural language processing techniques to better match disputant case descriptions (informal and concise) with court decisions (formal and verbose). Experimental results confirm the ability of the proposed solution to empower court decision retrieval, enabling therefore a well-informed eMediation process.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
eJRM - Information Retrieval System.
The acronym of eJRM-IRS is [BLIND].
For the Italian language a Snowball stemmer has been used and extended.
Court decisions are a priori labelled by legal experts.
To avoid confusion, the estimation of Coherence Similarity is based on non-normalized frequency of terms both for the query and the document.
Court decisions are obtained by crawling from the website http://www.ricercagiuridica.com/sentenze/. The dataset, after crawling, has been manually labeled by three legal experts.
Weka and SVMLIB libraries have been used for classification purposes. EJML (Efficient Java Matrix Library) has been adopted for dealing with large and sparse matrices and developing PCA-based feature reduction.
A random seed has been used to randomize the dataset to subsequently extract nine-folds as training and one-fold as testing.
Results about the classification have been micro-averaged.
These methods only compute the similarity between the court decisions and the disputant case description.
References
Ashley KD, Brüninghaus S (2009) Automatically classifying case texts and predicting outcomes. Artif Intell Law 17:152–165
Bellucci E, Zeleznikow J (2001) Family winner: a computerized negotiation support system which advises upon australian family law. In: ISDSS2001, pp 74–85
Brüninghaus S, Ashley KD (1997) Finding factors: learning to classify case opinions under abstract fact categories. In: Proceedings of the sixth international conference on artificial intelligence and law. ACM, New York, pp 123–131
Brüninghaus S, Ashley KD (2001) The role of information extraction for textual CBR. In: Proceedings of the 4th international conference on case-based reasoning (ICCBR-01), Vancouver, CA. Springer Lecture Notes in Artificial Intelligence, Springer, Berlin
Carneiro D, Novais P, Andrade F, Zeleznikow J, Neves J (2012) Using case-based reasoning and principled negotiation to provide decision support for dispute resolution. Knowl Inform Syst 36(3):789–826
Carneiro D, Novais P, Andrade F, Zeleznikow J, Neves J (2014) Online dispute resolution: an artificial intelligence perspective. Artif Intell Rev 41(2):211–240
Chang C-C, Lin C-J (2001) LIBSVM: a library for support vector machines. Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
Craswell Nick (2009) Precision at n. Encyclopedia of database systems, pp 2127–2128
Fersini E, Messina E, Manenti L, Bagnara G, El Jelali S, Arosio G (2014) eMediation: towards smart online dispute resolution. In: KMIS 2014-Proceedings of the international conference on knowledge management and information sharing, pp 228–236
Jarvelin K, Kekalainen J (2002) Cumulated gain-based evaluation of IR techniques. ACM Trans Inf Syst 20(4):422–446
Gomez JC, Boiy E, Moens M-F (2012) Highly discriminative statistical features for email classication. Knowl Inform Syst 31(1):23–53
Hervé A, Lynne JW (2010) Overview: principal component analysis. WIREs Comput Stat 2(4):433–459
Langley Pat, Iba Wayne, Thompson Kevin (1992) An analysis of bayesian classifiers. In: Proceedings of the tenth national conference on artificial intelligence, AAAI92. AAAI Press, pp 223–228
Moens M-F, Gebruers R, Uyttendaele C (1996) SALOMON: final report. Technical Report ICRI, K:U. Leuven
Moens M-F, Uyttendaele C, Dumortier J (1999) Information extraction from legal texts: the potential of discourse analysis. Int J Hum-Comput Stud 51:1155–1171
Moens M-F (2001) Innovative techniques for legal text retrieval. Artif Intell Law 9:29–57
Quinlan JR (1993) C4. 5: programs for machine learning, vol 1. Morgan kaufmann, Burlington
Riloff E (1996) Automatically generating extraction patterns from untagged text. In: Proceedings of the national conference on artificial intelligence, pp 1044–1049
Rodrguez-Doncel V, Santos C, Casanovas P (2014) Ontology-driven legal support-system in the air transport passenger domain. In: Proceedings of 2014 international workshop on semantic web for the law
Rodrguez-Doncel Vctor, Santos Cristiana, Casanovas Pompeu (2014) A model of air transport passenger incidents and rights. In: Frontiers in artificial intelligence and applications series
Stranieri A, Zeleznikow J (1995) The Split_Up system: Integrating neural networks and rule-based reasoning in the legal domain. In: Proceedings of the fifth international conference on artificial intelligence and law
Uijttenbroek EM, Lodder AR, Klein MCA, Wildeboer GR, van Steenbergen WR, Sie LL, Huygen PEM, van Harmelen F (2008) Retrieval of case law to provide Layman with information about liability: preliminary results of the BEST-project. In: Computable models of the law
Vapnik V (1998) Statistical learning theory, vol 2. Wiley, New York
Wu T-F, Lin C-J, Wend RC (2004) Probability estimates for multi-class classification by pairwise coupling. J Mach Learn Res 5:975–1005
Yiming Y, Pedersen JO (1997) A comparative study on feature selection in text categorization. In: Proceedings of the fourteenth international conference on machine learning. Morgan Kaufmann Publishers Inc, pp 412–420
Zeleznikow J, Meersman R, Hunter D, van Helvoort E (1995) Computer tools for aiding legal negotiation. In: Proceedings of the 6th Australasian conference on information systems
Acknowledgments
This work is partially funded by the eJRM Project (ref.: PON01_01286).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
El Jelali, S., Fersini, E. & Messina, E. Legal retrieval as support to eMediation: matching disputant’s case and court decisions. Artif Intell Law 23, 1–22 (2015). https://doi.org/10.1007/s10506-015-9162-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10506-015-9162-1