Abstract Laws are often developed in a piecemeal approach and many provisions of similar nature are often found in different legislations. Therefore, there is a need to classify legislations into various legal topics to help legal professionals in their daily activities. In this study, we have experimented with various deep learning architectures for the automatic classification of 490 legislations from the Republic of Mauritius into 30 categories. Our results demonstrate that a Deep Neural Network (DNN) with three hidden layers delivered the best performance compared with other architectures such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs). A mean classification accuracy of 60.9% was achieved using DNN, 56.5% for CNN and 33.7% for Long Short-Term Memory (LSTM). Comparisons were also made with traditional machine learning classifiers such as support vector machines and decision trees and it was found that the performance of DNN was superior, by at least 10%, in all runs. Both general pre-trained word embeddings such as Word2vec and domain-specific word embeddings such as Law2vec were used in combination with the above deep learning architectures but Word2vec had the best performance. To our knowledge, this is the first application of deep learning in the categorisation of legislations.

References

[1] Bilgin M. and Koktas H., “Sentiment Analysis with Term Weighting and Word Vectors,” The International Arab Journal of Information and Technology, vol. 16, no. 5, pp. 953-959, 2019.

[2] Boella G., Caro L., and Humphreys L., “Using Classification to Support Legal Knowledge Engineers in the Eunomos Legal Document Management System,” in Proceedings of 5th International Workshop on Juris-informatics, Kagawa, 2011.

[3] Burns G., Li X., and Peng N., “Building Deep Learning Models for Evidence Classification from the Open Access Biomedical Literature,” Database, vol. 1019, 2019.

[4] Chalkidis I. and Androutsopoulos I., “A Deep Learning Approach to Contract Element Extraction,” in Proceedings of 30th International Conference on Legal Knowledge and Information Systems, Luxembourg, pp. 155-164, 2017.

[5] Chalkidis I. and Kampas D., “Deep Learning in Law: Early Adaptation and Legal Word Embeddings Trained on Large Corpora,” Artificial Intelligence and Law, vol. 27, pp. 171- 198, 2019.

[6] Chollet F., Deep Learning with Python, Manning Publications Co, 2018.

[7] Collarana D., Heuss T., Lehmann J., Lytra I., Maheshwari, G., Nedelchev R., and Trivedi P., “A Question Answering System on Regulatory Documents,” in Proceedings of 31st Annual Conference on Legal Knowledge and Information Systems, Groningen, pp. 41-50, 2018.

[8] Curran T. and Thompson P., “Automatic Categorization of Statute Documents,” in Proceedings of the 8th ASIS SIGICR Classification Research Workshop, Washington, pp. 19-30, 1997.

[9] De Maat E. and Winkels R., “Automatic Classification of Sentences in Dutch Laws,” in Proceedings of 21st Annual Conference on Legal Knowledge and Information Systems, Florence, pp. 207-216, 2008.

[10] Francesconi E. and Passerini A., “Automatic Classification of Provisions in Legislative Texts,” Artificial Intelligence and Law, vol. 15, no. 1, pp. 1-17, 2007.

[11] Giri R., Porwal Y., Shukla V., Chadha P., and Kaushal R., “Approaches for Information Classification of Legislations using Deep Learning 661 Retrieval in Legal Documents,” in Proceedings of 10th International Conference on Contemporary Computing, Noida, pp. 1-6, 2017.

[12] Goltz N. and Mayo M., “Enhancing Regulatory Compliance by Using Artificial Text Mining to Identify Penalty Clauses in Legislation,” in Proceedings of the International Workshop on Mining and Reasoning with Legal Text, London, pp. 1-9, 2017.

[13] John A., Luigi D., Guido B., and Cesare B., “An Approach to Information Retrieval and Question Answering in the Legal Domain,” in Proceedings of 10th International Workshop on Juris- informatics, Kanagawa, pp. 1-14, 2016.

[14] Kastrati Z., Imran A., and Yayilgan S., “the Impact of Deep Learning on Document Classification Using Semantically Rich Representations,” Information Processing and Management, vol. 56, no. 5, pp. 1618-1632, 2019.

[15] Kim Y., “Convolutional Neural Networks for Sentence Classification,” in Proceedings of the Conference on Empirical Methods in Natural Language Processing, Doha, pp. 1746-1751, 2014.

[16] Kowsari K., Brown D., Heidarysafa M., Meimandi K., Gerber M., and Barnes L., “HDLTex: Hierarchical Deep Learning for Text Classification,” in Proceedings of the 16th IEEE International Conference on Machine Learning and Applications, Cancun, pp. 364-371 2017.

[17] Kowsari K., Meimandi K., Heidarysafa M., Mendu S., Barnes L., and Brown D., “Text Classification Algorithms: A Survey,” Information, vol. 10, no. 4, 2019.

[18] Lai S., Xu L., Liu K., and Zhao J., “Recurrent Convolutional Neural Networks for Text Classification,” in Proceedings of the 29th AAAI Conference on Artificial Intelligence, Austin, pp. 2267-2273, 2015.

[19] Lippi M., Palka P., Contissa G., Lagioia F., Micklitz H., Sartor G., and Torroni P., “CLAUDETTE: An Automated Detector of Potentially Unfair Clauses in Online Terms of Service,” Artificial Intelligence and Law, vol. 27, no. 2, pp. 117-139, 2019.

[20] Liu L., Liu K., Cong Z., Zhao J., Ji Y., and He J., “Long Length Document Classification by Local Convolutional Feature Aggregation,” Algorithms, vol. 11, no. 8, pp. 108, 2018.

[21] Luo B., Feng Y., Xu J., Zhang X., and Zhao D., “Learning to Predict Charges for Criminal Cases with Legal Basis,” in Proceedings of Conference on Empirical Methods in Natural Language Processing, Copenhagen, pp. 2727-2736, 2017.

[22] Mikolov T., Sutskever I., Chen K., Corrado G., and Dean J., “Distributed Representations of Words and Phrases and their Compositionality,” in Proceedings of the 27th Conference on Advances in Neural Information Processing Systems, Lake Tahoe, pp. 3111-3119, 2013.

[23] Nguyen G., Dlugolinsky S., Bobak M., Tran V., Garcia A., Heredia I., Malik P., and Hluchy L., “Machine Learning and Deep Learning Frameworks and Libraries for Large-Scale Data Mining: A Survey,” Artificial Intelligence Review, vol. 52, pp. 77-124, 2019.

[24] O'neill J., Buitelaar P., Robin C., and Brien L., “Classifying Sentential Modality in Legal Language: A Use Case in Financial Regulations, Acts and Directives,” in Proceedings of the 16th International Conference on Artificial Intelligence and Law, London, pp. 159-168, 2017.

[25] Purpura S. and Hillard D., “Automated Classification of Congressional Legislation,” in Proceedings of the 7th Annual International Conference on Digital Government Research, San Diego, pp. 219-225, 2006.

[26] Undavia S., Meyers A., and Ortega J., “A Comparative Study of Classifying Legal Documents with Neural Network,” in Proceedings of the Federated Conference on Computer Science and Information Systems, Poznan, pp. 515-522, 2018.

[27] Van-Noortwijk K., Visse J., and De Mulder R., “Ranking and Classifying Legal Documents using Conceptual Information,” Journal of Information, Law and Technology, vol. 2006, pp. 1-15, 2006.

[28] Waltl B., Bonczek G., Scepankova E., and Matthes F., “Semantic Types of Legal Norms in German Laws: Classification and Analysis Using Local Linear Explanations,” Artificial Intelligence and Law, vol. 27, no. 1, pp. 43-71, 2019.

[29] Yang Z., Yang D., Dyer C., He X., Smola A., and Hovy E., “Hierarchical Attention Networks for Document Classification,” in Proceedings of the Conference on the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, pp. 1480-1489, 2016. 662 The International Arab Journal of Information Technology, Vol. 18, No. 5, September 2021 Sameerchand Pudaruth is a Senior Lecturer and Head of the ICT Department at the University of Mauritius. He has a PhD in Artificial Intelligence (AI) from the University of Mauritius. He is a Senior member of IEEE, founding member of the IEEE Mauritius Subsection and the current Vice-Chair of the IEEE Mauritius Section. He is also a member of the Association for Computing Machinery (ACM). His research interests are Artificial Intelligence, Machine Learning, Data Science, Machine Translation, Computer Vision, Robotics, Mobile Applications, Web Technologies, Multimedia, Blockchain and Information Technology Law. He has written more than 70+ papers for national and international journals and conferences. He has been in the organising committee of many successful international conferences. Sunjiv Soyjaudah obtained his LLB (Hons) degree from the University of London. He was called to the Bar of England and Wales at the Honourable Society of the Middle Temple and subsequently joined the Mauritian Bar. He is presently the Head of Soyjaudah Chambers. He has been the Dean of the Faculty of Engineering at the University of Mauritius. He successfully supervised over 20 PhD students and 2 post-doctoral fellows. He has published over 250 research papers in international journals and conferences. He was successively appointed Executive Director of the Tertiary Education Commission and the Information and Communications Technologies Authority. Rajendra Gunputh is the Dean of the Faculty of Law and Management at the University of Mauritius with a Personal Chair in International Comparative Law with Specialisation in Employment Law and Trade Union Law. He holds a double PhD (Law) from the l’Université Paris V-René Descartes (France) in Public Law and l’Université de la Réunion in Private Law both with the highest distinctions (First Class). He is currently the Dean of the Faculty of Law and Management at the University of Mauritius. He has authored more than 100 articles which have been published worldwide and several treaties on Mauritian Law and various books and manuals on Law (Labour Law, Media Law, International Humanitarian Law).