Prediction of Turkish Constitutional Court Decisions in Terms of Admissibility and Violation of Rights With Artificial Intelligence

Abstract

The digitization of legal texts and advances in information processing theories and technologies have triggered several transformations in both the practice and teaching of law in recent years. Techniques developed in areas such as artificial intelligence, natural language processing, text mining, and machine learning have drawn the attention of legal practitioners and academics to this field. It is possible to remove obstacles to access to justice, improve legal security and certainty, and solve practical problems faced by legal practitioners by employing assistive tools to be created by using artificial intelligence technologies in the field of law. This study aims to develop an algorithm to predict the results of the Constitutional Court of the Republic of Türkiye on individual applications in terms of admissibility and whether there is a violation of rights by using machine learning and natural language processing techniques. In the study, the texts in the "Facts" title of the reference texts were used. A success rate of 91.56% was achieved for admissibility and 97.18% for whether there was a violation of rights. The study is unique in its field in that it performs a two-stage prediction task regarding admissibility and merit, provides a highly representative model since it includes all processable data, does not use a data augmentation method, and has a high success rate.

Keywords

• Constitutional Court
• artificial intelligence
• individual application
• violation of rights
• admissibility

Prediction of Turkish Constitutional Court Decisions in Terms of Admissibility and Violation of Rights With Artificial Intelligence

Abstract

Hukuk metinlerinin dijitalleştirilmesi ve bilgi işleme teorileri ve teknolojilerindeki ilerlemeler, son yıllarda hukukun hem uygulamasında hem de öğretiminde çeşitli dönüşümleri tetiklemiştir. Yapay zeka, doğal dil işleme, metin madenciliği ve makine öğrenmesi gibi alanlarda geliştirilen teknikler, hukuk uygulayıcılarının ve akademisyenlerin dikkatini bu alana çekmiştir. Hukuk alanında yapay zeka teknolojilerinin kullanılmasıyla oluşturulacak yardımcı araçların kullanılmasıyla adalete erişimin önündeki engellerin kaldırılması, hukuki güvenliğin ve kesinliğin artırılması ve hukuk uygulayıcılarının karşılaştığı pratik sorunların çözülmesi mümkündür. Bu çalışmada, makine öğrenmesi ve doğal dil işleme tekniklerini kullanarak Türkiye Cumhuriyeti Anayasa Mahkemesi'nin bireysel başvurulara ilişkin kabul edilebilirlik ve hak ihlali olup olmadığı açısından sonuçlarını tahmin eden bir algoritma geliştirmeyi amaçlamaktadır. Çalışmada, referans metinlerin "Olgular" başlığındaki metinler kullanılmıştır. Kabul edilebilirlik için %91,56, hak ihlali olup olmadığı için %97,18 başarı oranı elde edilmiştir. Çalışma, kabul edilebilirlik ve liyakat konusunda iki aşamalı bir tahmin görevi gerçekleştirmesi, tüm işlenebilir verileri içerdiğinden oldukça temsili bir model sunması, veri artırma yöntemi kullanmaması ve yüksek bir başarı oranına sahip olması bakımından kendi alanında benzersizdir.

Keywords

• Anayasa Mahkemesi
• yapay zeka
• bireysel başvuru
• hak ihlali
• kabul edilebilirlik

References

1. Davies G. The Relationship between Empirical Legal Studies and Doctrinal Legal Research. Erasmus Law Review. 2020;13(2):3–12. doi:10.5553/ELR.000141.
2. Frankenreiter J, Livermore MA. Computational Methods in Legal Analysis. Annual Review of Law and Social Science. 2020;16(1):39–57. doi:10.1146/annurev-lawsocsci-052720-121843.
3. Hutchinson T, Duncan N. Defining and Describing What We Do: Doctrinal Legal Research. Deakin Law Review. 2012;17(1):83–120.
4. Kazmierski V. How Much “Law” in Legal Studies? Approaches to Teaching Legal Research and Doctrinal Analysis in a Legal Studies Program. Canadian Journal of Law and Society. 2014;29(3):297–310.
5. Taekema S. Methodologies of Rule of Law Research: Why Legal Philosophy Needs Empirical and Doctrinal Scholarship. Law and Philosophy. 2021;40(1):33–66. doi:10.1007/s10982-020-09388-1.
6. Alarie B, Niblett A, Yoon AH. How artificial intelligence will affect the practice of law. University of Toronto Law Journal. 2018;68(Suppl 1):106–24. doi:10.3138/utlj.2017-0052.
7. Mumcuoğlu E, Öztürk CE, Ozaktas HM, Koç A. Natural Language Processing in Law: Prediction of Outcomes in the Higher Courts of Turkey. Information Processing & Management. 2021;58(5):102684. doi:10.1016/j.ipm.2021.102684.
8. Medvedeva M, Vols M, Wieling M. Using Machine Learning to Predict Decisions of the European Court of Human Rights. Artificial Intelligence and Law. 2020;28(2):237–66. doi:10.1007/s10506-019-09255-y.

9. Surden H. Machine Learning and Law. Washington Law Review. 2014;89(1):87–115.
10. Agrawal K. Legal Case Summarization: An Application for Text Summarization. 2020 International Conference on Computer Communication and Informatics (ICCCI). 2020:1–6. doi:10.1109/ICCCI48352.2020.9104093.
11. Hachey B, Grover C. Extractive summarisation of legal texts. Artificial Intelligence and Law. 2007;14(4):305–45. doi:10.1007/s10506-007-9039-z.
12. Sheik R, Nirmala SJ. Deep Learning Techniques for Legal Text Summarization. 2021 IEEE 8th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON). 2021:1–5.
13. Sil R, Alpana, Roy A, Dasmahapatra M, Dhali D. An Intelligent Approach for Automated Argument-Based Legal Text Recognition and Summarization Using Machine Learning. Journal of Intelligent & Fuzzy Systems. 2021;41(5):5457–66. doi:10.3233/JIFS-189867.
14. Dixon JHB. What Judges and Lawyers Should Understand About Artificial Intelligence Technology. Judges’ Journal. 2020;59(1):36–8.
15. Reiling AD. Courts and Artificial Intelligence. International Journal for Court Administration. 2020;11(2):8. doi:10.36745/ijca.343.
16. Wang N. “Black Box Justice”: Robot Judges and AI-Based Judgment Processes in China’s Court System. 2020 IEEE International Symposium on Technology and Society (ISTAS). 2020:58–65. doi:10.1109/ISTAS50296.2020.9462216.
17. Katz DM. Quantitative Legal Prediction—Or—How I Learned to Stop Worrying and Start Preparing for the Data-Driven Future of the Legal Services Industry. Emory Law Journal. 2013;62(4):909–66.
18. Kızrak MA, Buluz B, Özparlak BO, Ünsal B, Durlu Gürzümar D, Deniz Atalar G, et al. Law in the Era of Artificial Intelligence [Joint Workshop]. The Bar of Istanbul, Ankara and İzmir; 2019. Available from: https://www.istanbulbarosu.org.tr/ files/docs/Yapay_Zeka_Caginda_Hukuk2019.pdf
19. Virtucio MBL, Aborot JA, Abonita JKC, Avinante RS, Copino RJB, Neverida MP, et al. Predicting Decisions of the Philippine Supreme Court Using Natural Language Processing and Machine Learning. 2018 IEEE 42nd Annual Computer Software and Applications Conference (COMPSAC). 2018:130–5. doi:10.1109/COMPSAC.2018.10348.
20. Wu T. Will Artificial Intelligence Eat the Law: The Rise of Hybrid Social-Ordering Systems. Columbia Law Review. 2019;119(7):2001–28.
21. Lage-Freitas A, Allende-Cid H, Santana O, de Oliveira-Lage L. Predicting Brazilian Court Decisions. arXiv:1905.10348 [Cs]. 2019. Available from: http://arxiv.org/abs/1905.10348
22. Ruger TW, Kim PT, Martin AD, Quinn KM. The Supreme Court Forecasting Project: Legal and Political Science Approaches to Predicting Supreme Court Decisionmaking. Columbia Law Review. 2004;104(4):1150. doi:10.2307/4099370.
23. Shaikh RA, Sahu TP, Anand V. Predicting Outcomes of Legal Cases Based on Legal Factors Using Classifiers. Procedia Computer Science. 2020;167:2393–402. doi:10.1016/j.procs.2020.03.292.
24. Osbeck MK, Gilliland M. Outcome Prediction in the Practice of Law. Foresight: The International Journal of Applied Forecasting. 2018;50:42–8.
25. Aletras N, Tsarapatsanis D, Preoţiuc-Pietro D, Lampos V. Predicting judicial decisions of the European Court of Human Rights: A Natural Language Processing perspective. PeerJ Computer Science. 2016;2:e93. doi:10.7717/peerj-cs.93.
26. Goel S, Roshan S, Tyagi R, Agarwal S. Augur Justice: A Supervised Machine Learning Technique To Predict Outcomes Of Divorce Court Cases. 2019 Fifth International Conference on Image Information Processing (ICIIP). 2019:280–5.
27. Li J, Zhang G, Yan H, Yu L, Meng T. A Markov Logic Networks Based Method to Predict Judicial Decisions of Divorce Cases. 2018 IEEE International Conference on Smart Cloud (SmartCloud). 2018:129–32. doi:10.1109/SmartCloud.2018.00029.
28. Kowsrihawat K, Vateekul P, Boonkwan P. Predicting Judicial Decisions of Criminal Cases from Thai Supreme Court Using Bi-directional GRU with Attention Mechanism. 2018 5th Asian Conference on Defense Technology (ACDT). 2018:50–5. doi:10.1109/ACDT.2018.8592948.
29. Chen B, Li Y, Zhang S, Lian H, He T. A Deep Learning Method for Judicial Decision Support. 2019 IEEE 19th International Conference on Software Quality, Reliability and Security Companion (QRS-C). 2019:145–9. doi:10.1109/QRS-C.2019.00040.
30. Contini F. Artificial Intelligence and the Transformation of Humans, Law and Technology Interactions in Judicial Proceedings. Law, Technology and Humans. 2020;2(1):4–18. doi:10.5204/lthj.v2i1.1478.
31. Yuan D. Case Study of Criminal Law Based on Multi-Task Learning. 2020 International Conference on Artificial Intelligence and Computer Engineering (ICAICE). 2020:98–103. doi:10.1109/ICAICE51518.2020.00025.
32. Long S, Tu C, Liu Z, Sun M. Automatic Judgment Prediction via Legal Reading Comprehension. arXiv:1809.06537 [Cs]. 2018. Available from: http://arxiv.org/abs/1809.06537
33. Sert MF, Yıldırım E, Haşlak İ. Using Artificial Intelligence to Predict Decisions of the Turkish Constitutional Court. Social Science Computer Review. 2021;089443932110103. doi:10.1177/08944393211010398.
34. O’Sullivan C, Beel J. Predicting the Outcome of Judicial Decisions Made by the European Court of Human Rights. arXiv:1912.10819 [Cs, Stat]. 2019. Available from: http://arxiv.org/abs/1912.10819
35. Fendoğlu HT. Anayasa Yargısı. 4th ed. Yetkin Yayınları; 2020.
36. Gözler K. Anayasa Hukukunun Genel Esasları. 12th ed. Ekin Yayıncılık; 2020.
37. İnceoğlu S. Anayasa Mahkemesi’ne Bireysel Başvuru: Türkiye ve Latin Modelleri. 1st ed. Oniki Levha Yayınları; 2017.
38. Göztepe E. Türkiye’de Anayasa Mahkemesi’ne Bireysel Başvuru Hakkının (Anayasa Şikâyeti) 6216 Sayılı Kanun Kapsamında Değerlendirilmesi. Türkiye Barolar Birliği Dergisi. 2011;95.
39. Fagan F. Natural Language Processing for Lawyers and Judges. SSRN Electronic Journal. 2020. doi:10.2139/ssrn.3564966.
40. Lawlor RC. What Computers Can Do: Analysis and Prediction of Judicial Decisions. American Bar Association Journal. 1963;49(4):337–44.
41. Ekinci H. Anayasa Mahkemesine Bireysel Başvuruda Kabul Edilebilirlik Kriterleri ve İnceleme Yöntemi. Anayasa Yargısı. 2013;30.
42. Şirin T. Türkiye’de Anayasa Şikayeti (Bireysel Başvuru). 1st ed. Oniki Levha Yayınları; 2013.
43. Akyel R. Bireysel Başvuru Yolu: Misyonu, Vizyonu Ve Uygulanması. Adalet Dergisi. 2022;68(1):53–92.
44. Kılıç A. Anayasa Mahkemesinin Bireysel Başvuru Kararlarının Türkiye Büyük Millet Meclisine Bildirilmesi. Anayasa Dergisi. 2021;38(1).
45. Azaklı M. Bireysel Başvuru Usulü, Süre ve Temellendirilmemiş Şikâyet. Bireysel Başvuruda İş Yükü ve Çözüm Önerileri Sempozyumu. 2022. p.17–32.
46. Şulea OM, Zampieri M, Vela M, van Genabith J. Predicting the Law Area and Decisions of French Supreme Court Cases. RANLP 2017—Recent Advances in Natural Language Processing Meet Deep Learning. 2017:716–22. doi:10.26615/978-954-452-049-6_092.
47. Aydin ÖD. Türk Anayasa Yargısında Yeni Bir Mekanizma: Anayasa Mahkemesi’ne Bireysel Başvuru. Gazi Üniversitesi Hukuk Fakültesi Dergisi. 2011;15(4).
48. Tekbaş DA. Anayasa Mahkemesi Bireysel Başvuru İstatistiklerinin Değerlendirilmesi. Anayasa Dergisi. 2018;35.
49. Ekinci H. Anayasa Mahkemesinin Bireysel Başvuru İş Yükü, Çözüme Yönelik Mahkeme Pratiği ve Öneriler. Uyuşmazlık Mahkemesi Dergisi. 2015;5(5). doi:10.18771/umd.58105.
50. Sharda R, Delen D, Turban E. Analytics, Data Science, & Artificial Intelligence: Systems for Decision Support. Pearson Education, Inc; 2020.
51. Zhai C, Massung S. Text Data Management and Analysis: A Practical Introduction to Information Retrieval and Text Mining. Association for Computing Machinery and Morgan & Claypool; 2016.
52. Çetin FS, Eryiğit G. Türkçe Hedef Tabanlı Duygu Analizi İçin Alt Görevlerin İncelenmesi–Hedef Terim, Hedef Kategori ve Duygu Sınıfı Belirleme. Bilişim Teknolojileri Dergisi. 2018;11(1):43–56.
53. Vidgen B, Derczynski L. Directions in Abusive Language Training Data, A Systematic Review: Garbage in, Garbage Out. PLOS One. 2020;15(12):e0243300.
54. Geiger RS, Yu K, Yang Y, Dai M, Qiu J, Tang R, Huang J. Garbage in, garbage out? Do machine learning application papers in social computing report where human-labeled training data comes from? Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. 2020:325–36.
55. Jo T. Text Mining: Concepts, Implementation, and Big Data Challenge. Studies in Big Data. Springer International Publishing; 2018.
56. Anandarajan M, Hill C, Nolan T. Practical text analytics. Maximizing the Value of Text Data. Springer; 2019.
57. Aravi G. Metin Madenciliği ile Sosyal Medya Analizi [Yüksek Lisans Tezi]. İstanbul: İstanbul Aydın Üniversitesi; 2014.
58. Weiss SM, Indurkhya N, Zhang T, Damerau F. Text Mining: Predictive Methods for Analyzing Unstructured Information. Springer, New York; 2005.
59. Cady F. The data science handbook. John Wiley & Sons; 2017.
60. Mikolov T, Chen K, Corrado G, Dean J. Efficient Estimation of Word Representations in Vector Space. Proceedings of Workshop at ICLR. 2013.
61. Jang B, Kim I, Kim JW. Word2vec Convolutional Neural Networks for Classification of News Articles and Tweets. PloS One. 2019;14(8):e0220976.
62. Goldberg Y, Levy O. word2vec Explained: Deriving Mikolov et al.’s Negative-Sampling Word-Embedding Method. arXiv preprint arXiv:1402.3722. 2014.
63. De Boom C, Van Canneyt S, Bohez S, Demeester T, Dhoedt B. Learning semantic similarity for very short texts. 2015 IEEE International Conference on Data Mining Workshop (ICDMW). 2015:1229–34.
64. Le Q, Mikolov T. Distributed Representations of Sentences and Documents. In: International Conference on Machine Learning; 2014. p. 1188–96.
65. Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Machine Learning. 2006;63:3–42.
66. Dietterich T. Overfitting and undercomputing in machine learning. ACM Computing Surveys. 1995;27(3):326–7.
67. Moore AW. Cross-Validation for Detecting and Preventing Overfitting. School of Computer Science, Carnegie Mellon University; 2001.
68. Polikar R. Ensemble Learning. In: Zhang C, Ma Y, editors. Ensemble Machine Learning. Springer, Boston, MA; 2012. p. 1–34.
69. Kim MJ, Kang DK. Ensemble with Neural Networks for Bankruptcy Prediction. Expert Systems with Applications. 2010;37(4):3373–9.
70. Brownlee J. Better deep learning: train faster, reduce overfitting, and make better predictions. Machine Learning Mastery; 2018.
71. Schütze, H., Manning, C. D., & Raghavan, P. (2008). Introduction to information retrieval. Cambridge: Cambridge University Press. p.129-130
72. Coulombe C. Text Data Augmentation Made Simple By Leveraging NLP Cloud APIs. ArXiv:1812.04718 [Cs]. 2018. Available from: http://arxiv.org/abs/1812.04718
73. Constitutional Court Of The Republic Of Turkey. Individual Application Statistics (23/9/2012—31/12/2022). 2022.
74. Mikolov, T., Kopecky, J., Burget, L., & Glembek, O. (2009, April). Neural network based language models for highly inflective languages. In 2009 IEEE international conference on acoustics, speech and signal processing (pp. 4725-4728). IEEE.