Skip to main content
Top

03-11-2024 | Original Research

Advancing legal recommendation system with enhanced Bayesian network machine learning

Authors: Xukang Wang, Vanessa Hoo, Mingyue Liu, Jiale Li, Ying Cheng Wu

Published in: Artificial Intelligence and Law

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The integration of machine learning algorithms into the legal recommendation system marks a burgeoning area of research, with a particular focus on enhancing the accuracy and efficiency of judicial decision-making processes. The application of Bayesian Network (BN) emerges as a potent tool in this context, promising to address the inherent complexities and unique nuances of legal texts and individual case subtleties. However, the challenge of achieving high accuracy in BN parameter learning, especially under conditions of limited data, remains a significant hurdle. This study proposes an Enhanced Maximum Parameter Learning (EMPL) algorithm, tailored for BN parameter optimization in scenarios characterized by small sample sizes. The EMPL algorithm, innovatively incorporating the Synthetic Minority Over-sampling Technique (SMOTE), begins with the formulation of inequality constraints derived from domain expertise. It establishes a minimal dataset threshold necessary for effective parameter learning. Through the introduction of an index weighting factor function that dynamically adjusts according to the sample size, the algorithm facilitates the derivation of refined BN parameters. The core innovation of the EMPL algorithm lies in its use of an exponentially weighted factor function, designed to be responsive to variations in sample size, and its capacity to expand the parameter space using SMOTE to align with qualitative constraints from expert insights. This approach enables the integration of data-derived parameters with those obtained through expert experience in an exponentially weighted manner, culminating in the optimization of BN parameters. Comparative analysis reveals that the EMPL algorithm achieves superior learning accuracy over traditional Maximum Likelihood Estimation (MLE) and qualitative maximum a posteriori (QMAP) approach, particularly in contexts of sparse data. Furthermore, it demonstrates enhanced performance relative to variable weight learning algorithms, underscoring its potential to significantly improve decision-making processes in the legal domain through advanced BN parameter learning.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literature
go back to reference Berkenkamp F, Krause A, Schoellig AP (2023) Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics[J]. Mach Learn 112(10):3713–3747MathSciNetCrossRef Berkenkamp F, Krause A, Schoellig AP (2023) Bayesian optimization with safety constraints: safe and automatic parameter tuning in robotics[J]. Mach Learn 112(10):3713–3747MathSciNetCrossRef
go back to reference Chae Y (2020a) US AI regulation guide: legislative overview and practical considerations. J Robot Artif Intell Law 3:17 Chae Y (2020a) US AI regulation guide: legislative overview and practical considerations. J Robot Artif Intell Law 3:17
go back to reference Constant A (2024) A Bayesian model of legal syllogistic reasoning[J]. Artif Intell Law 32(2):441–462CrossRef Constant A (2024) A Bayesian model of legal syllogistic reasoning[J]. Artif Intell Law 32(2):441–462CrossRef
go back to reference Dremliuga R, Kuznetcov P, Mamychev A (2019) Criteria for recognition of AI as a legal person. J Pol L 12:105 Dremliuga R, Kuznetcov P, Mamychev A (2019) Criteria for recognition of AI as a legal person. J Pol L 12:105
go back to reference Fenton N, Neil M, Berger D (2016) Bayes and the law[J]. Ann Rev Stat Appl 3(1):51–77CrossRef Fenton N, Neil M, Berger D (2016) Bayes and the law[J]. Ann Rev Stat Appl 3(1):51–77CrossRef
go back to reference Gao G, Guang G, Hai D (2014) Learning Bayesian network parameters under dual constraints from small data set [J]. Acta Autom Sinica 40(07):1509–1516 Gao G, Guang G, Hai D (2014) Learning Bayesian network parameters under dual constraints from small data set [J]. Acta Autom Sinica 40(07):1509–1516
go back to reference Guo W, Kou X, Li M, Hou Y, Xiao QA (2022) BN parameter learning algorithm based on variable weight fusion for small datasets. Comput Eng Sci 44:916 Guo W, Kou X, Li M, Hou Y, Xiao QA (2022) BN parameter learning algorithm based on variable weight fusion for small datasets. Comput Eng Sci 44:916
go back to reference Ji Lei H, Tang XW, Qiu JN (2015) A Bayesian network approach for predicting seismic liquefaction based on interpretive structural modeling[J]. Georisk Assess Manag Risk Eng Syst Geohazards 9(3):200CrossRef Ji Lei H, Tang XW, Qiu JN (2015) A Bayesian network approach for predicting seismic liquefaction based on interpretive structural modeling[J]. Georisk Assess Manag Risk Eng Syst Geohazards 9(3):200CrossRef
go back to reference Koller D (2009) & Friedman, N. Principles and Techniques. MIT Press, Probabilistic Graphical Models Koller D (2009) & Friedman, N. Principles and Techniques. MIT Press, Probabilistic Graphical Models
go back to reference Luis R, Sucar LE, Morales EF (2010) Inductive transfer for learning Bayesian networks. Mach Learn 79(1–2):227–255MathSciNetCrossRef Luis R, Sucar LE, Morales EF (2010) Inductive transfer for learning Bayesian networks. Mach Learn 79(1–2):227–255MathSciNetCrossRef
go back to reference Oskamp A, Lauritsen M (2002) AI in law practice? So far, not much. Artif Intell Law 10:227CrossRef Oskamp A, Lauritsen M (2002) AI in law practice? So far, not much. Artif Intell Law 10:227CrossRef
go back to reference Pears R, Finlay J, Connor A M (2014) Synthetic Minority over-sampling technique (SMOTE) for predicting software build outcomes[J]. arXiv preprint Pears R, Finlay J, Connor A M (2014) Synthetic Minority over-sampling technique (SMOTE) for predicting software build outcomes[J]. arXiv preprint
go back to reference Rosadi D (2021) Improving machine learning prediction of peatlands fire occurrence for unbalanced data using SMOTE approach. In: 2021 International Conference on Data Science, Artificial Intelligence, and Business Analytics (DATABIA), 160–163 Rosadi D (2021) Improving machine learning prediction of peatlands fire occurrence for unbalanced data using SMOTE approach. In: 2021 International Conference on Data Science, Artificial Intelligence, and Business Analytics (DATABIA), 160–163
go back to reference Seixas FL, Zadrozny B, Laks J, Conci A, Saade DCM (2014) A Bayesian network decision model for supporting the diagnosis of dementia, Alzheimer’s disease and mild cognitive impairment. Comput Biol Med 51:140–158CrossRef Seixas FL, Zadrozny B, Laks J, Conci A, Saade DCM (2014) A Bayesian network decision model for supporting the diagnosis of dementia, Alzheimer’s disease and mild cognitive impairment. Comput Biol Med 51:140–158CrossRef
go back to reference Spaeth HJ, Epstein L, Segal JA, Martin AD, Ruger TJ, Benesh SC (2020) Supreme Court Database, Version 2020 Re- lease 01. Washington University Law, Washington Spaeth HJ, Epstein L, Segal JA, Martin AD, Ruger TJ, Benesh SC (2020) Supreme Court Database, Version 2020 Re- lease 01. Washington University Law, Washington
go back to reference Yan H et al (2020) Bayesian network-based modeling and operational adjustment of plantwide flotation industrial process. Ind Eng Chem Res 59(5):2025–2035CrossRef Yan H et al (2020) Bayesian network-based modeling and operational adjustment of plantwide flotation industrial process. Ind Eng Chem Res 59(5):2025–2035CrossRef
go back to reference Zhang Y, Hu Z (2022) Parameter learning of Bayesian network with multiplicative synergistic constraints[J]. Symmetry 14(7):1469CrossRef Zhang Y, Hu Z (2022) Parameter learning of Bayesian network with multiplicative synergistic constraints[J]. Symmetry 14(7):1469CrossRef
go back to reference Zhang T, Zhang T, Li C, Zhai X, Huo Q (2021) Complementary and alternative therapies for precancerous lesions of gastric cancer: a protocol for a Bayesian network meta analysis. Medicine 100(2):e24249. CrossRef Zhang T, Zhang T, Li C, Zhai X, Huo Q (2021) Complementary and alternative therapies for precancerous lesions of gastric cancer: a protocol for a Bayesian network meta analysis. Medicine 100(2):e24249. CrossRef
go back to reference Zhong H et al. (2020) How does NLP benefit legal system: A summary of legal artificial intelligence. arXiv preprint . Zhong H et al. (2020) How does NLP benefit legal system: A summary of legal artificial intelligence. arXiv preprint .
Metadata
Title
Advancing legal recommendation system with enhanced Bayesian network machine learning
Authors
Xukang Wang
Vanessa Hoo
Mingyue Liu
Jiale Li
Ying Cheng Wu
Publication date
03-11-2024
Publisher
Springer Netherlands
Published in
Artificial Intelligence and Law
Print ISSN: 0924-8463
Electronic ISSN: 1572-8382
DOI
https://doi.org/10.1007/s10506-024-09424-8

Premium Partner