LAW-U: Legal Guidance Through Artificial Intelligence Chatbot for Sexual Violence Victims and Survivors

被引：7

作者：

Socatiyanurak, Vorada ^{[1
,2
]}

Klangpornkun, Nittayapa ^{[1
,3
]}

Munthuli, Adirek ^{[1
,3
]}

Phienphanich, Phongphan ^{[1
,3
]}

Kovudhikulrungsri, Lalin ^{[4
]}

Saksakulkunakorn, Nantawat ^{[4
]}

Chairaungsri, Phonkanok ^{[4
]}

Tantibundhit, Charturong ^{[1
,3
]}

机构：

[1] Thammasat Univ, Ctr Excellence Intelligent Informat Speech & Lang, Rangsit Campus, Khlong Luang 12120, Pathum Thani, Thailand

[2] Univ Penn, Coll Arts & Sci, Philadelphia, PA 19104 USA

[3] Thammasat Univ, Fac Engn, Dept Elect & Comp Engn, Rangsit Campus, Khlong Luang 12120, Pathum Thani, Thailand

[4] Thammasat Univ, Fac Law, Rangsit Campus, Khlong Luang 12120, Pathum Thani, Thailand

来源：

IEEE ACCESS | 2021年 / 9卷

关键词：

Thai sexual violence law; sexual violence; legal artificial intelligence; chatbot; natural language processing; WORKERS; MEN;

D O I：

10.1109/ACCESS.2021.3113172

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Sexual violence is a severe and chronic occurrence around the world that has not been resolved. The stigmatized nature of sexual violence has forced victims and survivors to accept prejudiced accusations cultivated from discriminatory norms when they are never at fault nor responsible for such violations against their sexuality. LAW-U is an Artificial Intelligence (AI) chatbot that gives legal guidance to survivors of sexual violence by recommending the most relevant Supreme Court decisions to the survivors' situations. In Thai, "LAW-U'' - pronounced similarly to "(sic)'' - means "I will wait for you'', which signifies the chatbot's unconditional support to the user. 182 Thai Supreme Court cases of sexual violence, relating to Sections 276, 277, 278, and 279 of the Criminal Code, were used to develop Natural Language Processing (NLP) pipelines for LAW-U. Legal experts then generated mock-up dialogs from Supreme Court decisions which became the conversations used to train LAW-U. The computation of the similarity scores and the calculation of percentages of common keywords and keywords' synonyms were completed to increase the model's accuracy. When applying the model to the hold-out testing dataset, the accuracy was 88.89% for an exact match between the user's input and the Supreme Court case - this confirmed that LAW-U was ready for real-life application. LAW-U's unique design hopes to act as a precedent for other works at home and abroad to perpetuate awareness of sexual violence and eliminate any tolerance against these crimes by empowering sexual violence victims and survivors to reaffirm their inherent rights.

引用

页码：131440 / 131461

页数：22