人工智慧與法律資料分析之方法與應用：以單獨親權酌定裁判的預測模型為例

The Application of Artificial Intelligence and Legal Analytics: Focused on Decisions Regarding Child Custody

黃詩淳(Sieh-Chuen Huang) ； 邵軒磊(Hsuan-Lei Shao)

《臺大法學論叢》 48卷4期 (2019/12) Pp. 2023-2073

https://doi.org/10.6199/NTULJ.201912_48(4).0005

摘要

本文試圖應用人工智慧技術至法學問題。首先簡單介紹人工智慧的基本內涵，以及其分支技術機器學習的內容與功能為何，之後說明將其應用於法學研究，具體從事法律資料分析（legal analytics）之實益。其次，本文蒐集2012年1月1日至2014年12月31日共三年期間，當父母均為本國人、也都有意願爭取親權時，地方法院第一審共448件結果為「單獨親權」之裁判，包含了690位子女，使用機器學習當中的「梯度提升法（gradient boosting）」，分析其中民法第1055條之1的各項因素具有多高的重要性。研究發現，最重要的三項因素與比重分別是：主要照顧者為0.356，子女意願為0.267，親子互動為0.152；亦能明確指出其他各項因素的重要性程度。模型準確率（accuracy）為95.7 %，F1分數為0.927，表現相當良好。本文指出了在親權判決中，法官重視的因素以及重視的程度；人工智慧所建構的模型並能有效預測事件的結果，提高裁判的可預測性與透明性。如此，當事人與律師有更充足的資訊評估是否採取訴訟途徑，可能促進訴訟外紛爭解決（調解、和解）的使用率。惟須留意者，由於資料來源的限制，本文僅就公開裁判範圍預測；此外，法院如何判定共同監護、分別監護或第三人監護，亦待將來之研究。

關鍵字

人工智慧 ； 機器學習 ； 法律資料分析 ； 梯度提升法 ； 親權 ； 子女最佳利益 ； 法之可預測性

並列摘要

The remarkable advances in artificial intelligence influences human lives in almost every aspect including business and academic research. For example, it became more and more common to use machine learning techniques to analyze, categorize texts and predict outcomes, which can assist human in making more accurate decisions. This research attempts to explore the possibility to apply artificial intelligence approaches to legal studies. Firstly, this study introduces recent developments on artificial intelligence and the basic concepts regarding machine learning. Secondly, it explains how machine learning algorithms can be used to better predict legal outcomes. To demonstrate the strength of predictions, this article applies gradient boosting to analyze decisions related to child custody in Taiwan. We collected 448 cases from 2012 through 2014, involving 690 children whose parents were both Taiwanese and willing to acquire the custody, and in which the Taiwanese district court granted one parent sole custody. It is found that among factors enumerated in Article 1055-1 of Taiwan Civil Code, the three most important ones that judges consider are primary caregiver (gain=0.356), wishes of the child (gain=0.267), and parent-child interaction (gain=0.152). In terms of outcome predictions, the accuracy of the model is 95.7 % and F1 score is 0.927. The model built by gradient boosting could also demonstrate its application on individual cases - that is to say, it is able to reveal factors and how much they weighed on affecting the machine's prediction for a given case. By visualizing through waterfall charts, we may have a better understanding of criteria inside the machine's ＂mind＂. This clearly illustrates in custody disputes what factors and to what extent judges consider important in Taiwan. In addition, this effective predictive model can help improve the predictability and certainly of law. Based on this, divorce lawyers can preliminarily assess their clients' chances at winning divorce lawsuits and propose the most optimal dispute resolution strategy. The informational asymmetries leading to wasteful expenditure on litigation may be reduced. In the long run, legal analytics can improve the acquirability and affordability of information about legal rights and responsibilities, which will enhance public trust and confidence in judicial system.

並列關鍵字

artificial intelligence ； machine learning ； legal analytics ； gradient boosting ； child custody ； best interest of the child ； predictability of law

參考文獻

林琬真、郭宗廷、張桐嘉、顏厥安、陳昭如、林守德（2012），〈利用機器學習於中文法律文件之標記、案件分類及量刑預測〉，《中文計算語言學期刊》，17卷4期，頁49-67。

施慧玲、紀冠伶（2018），〈離婚訴訟「先搶先贏」的實務經驗敘事分析：兼論幼年子女最佳利益的司法裁量基準〉，《法令月刊》，69卷8期，頁75-102。

張永健、何漢葳、李宗憲（2017），〈或重於泰山、或輕於鴻毛：地方法院車禍致死案件慰撫金之實證研究〉，《政大法學評論》，149期，頁139-219。

陳顯武、陳世昌（2004），〈法資訊學上法本體論研究的興起與發展之分析：一個基本哲學概念意義之轉換〉，《臺大法學論叢》，33卷5期，頁1-49。

黃詩淳、邵軒磊（2018），〈酌定子女親權之重要因素：以決策樹方法分析相關裁判〉，《臺大法學論叢》，47卷1期，頁299-344。