APPCorp:a corpus for Android privacy policy document structure analysis

作     者：Shuang LIU Fan ZHANG Baiyang ZHAO Renjie GUO Tao CHEN Meishan ZHANG Shuang LIU;Fan ZHANG;Baiyang ZHAO;Renjie GUO;Tao CHEN;Meishan ZHANG

作者机构：College of Intelligence and ComputingTianjin UniversityTianjin 300372China School of New Media and CommunicationTianjin UniversityTianjin 300350China GoogleMountain ViewCA 94043USA 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2023年第17卷第3期

页      面：1-10页

核心收录：

学科分类：0839[工学-网络空间安全] 08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work was supported by the National Natural Science Foundation of China(Grant Nos.61802275 and U1836214) the Innovation fund of Tianjin University(2020XRG-0022) 

主　　题：privacy policy GDPR document structure analysis representation learning graph neural network 

摘      要：With the increasing popularity of mobile devices and the wide adoption of mobile Apps,an increasing concern of privacy issues is *** policy is identified as a proper medium to indicate the legal terms,such as the general data protection regulation(GDPR),and to bind legal agreement between service providers and ***,privacy policies are usually long and vague for end users to read and *** is thus important to be able to automatically analyze the document structures of privacy policies to assist user *** this work we create a manually labelled corpus containing 231 privacy policies(of more than 566,000 words and 7,748 annotated paragraphs).We benchmark our data corpus with 3 document classification models and achieve more than 82%on F1-score.