A comparative study of Chinese and European Internet companies' privacy policy based on knowledge graph
Wang, Yajing (2019-06-27)
A comparative study of Chinese and European Internet companies' privacy policy based on knowledge graph
(27.06.2019)
Julkaisu on tekijänoikeussäännösten alainen. Teosta voi lukea ja tulostaa henkilökohtaista käyttöä varten. Käyttö kaupallisiin tarkoituksiin on kielletty.
avoin
Julkaisun pysyvä osoite on:
https://urn.fi/URN:NBN:fi-fe2019070122495
https://urn.fi/URN:NBN:fi-fe2019070122495
Tiivistelmä
Privacy policy is not only a means of industry self-discipline, but also a way for users to protect their online privacy. The European Union (EU) promulgated the General Data Protection Regulation (GDPR) on May 25th, 2018, while China has no explicit personal data protection law. Based on knowledge graph, this thesis makes a comparative analysis of the Chinese and European Internet companies’ privacy policies, and combines with the relevant provisions of GDPR, puts forward suggestions on the privacy policy of Internet companies, so as to solve the problem of personal in-formation protection to a certain extent.
Firstly, this thesis chooses the process and methods of knowledge graph construction and analysis. The process of constructing and analyzing the knowledge graph is: data preprocessing, entity extraction, storage in graph database and query. Data preprocessing includes word segmentation and part-of-speech tagging, as well as text format adjustment. Entity extraction is the core of knowledge graph construction in this thesis. Based on the principle of Conditional Random Fields (CRF), CFR++ toolkit is used for the entity extraction. Subsequently, the extracted entities are transformed into “.csv” format and stored in the graph database Neo4j, so the knowledge graph is generated. Cypher query statements can be used to query information in the graph database.
The next part is about comparison and analysis of the Internet companies’ privacy policies in China and Europe. After sampling, the overall characteristics of the privacy policies of Chinese and European Internet companies are compared. According to the process of constructing knowledge graphs mentioned above, the “collected information” and “contact us” parts of the privacy policy are used to construct the knowledge graphs.
Finally, combined with the relevant content of GDPR, the results of the comparative analysis are further discussed, and suggestions are proposed. Although Chinese Internet companies’ privacy policies have some merits, they are far inferior to those of European Internet companies. China also needs to enact a personal data protection law according to its national conditions.
This thesis applies knowledge graph to the privacy policy research, and analyses Internet companies’ privacy policies from a comparative perspective. It also discusses the comparative results with GDPR and puts forward suggestions, and provides reference for the formulation of China's personal information protection law.
Firstly, this thesis chooses the process and methods of knowledge graph construction and analysis. The process of constructing and analyzing the knowledge graph is: data preprocessing, entity extraction, storage in graph database and query. Data preprocessing includes word segmentation and part-of-speech tagging, as well as text format adjustment. Entity extraction is the core of knowledge graph construction in this thesis. Based on the principle of Conditional Random Fields (CRF), CFR++ toolkit is used for the entity extraction. Subsequently, the extracted entities are transformed into “.csv” format and stored in the graph database Neo4j, so the knowledge graph is generated. Cypher query statements can be used to query information in the graph database.
The next part is about comparison and analysis of the Internet companies’ privacy policies in China and Europe. After sampling, the overall characteristics of the privacy policies of Chinese and European Internet companies are compared. According to the process of constructing knowledge graphs mentioned above, the “collected information” and “contact us” parts of the privacy policy are used to construct the knowledge graphs.
Finally, combined with the relevant content of GDPR, the results of the comparative analysis are further discussed, and suggestions are proposed. Although Chinese Internet companies’ privacy policies have some merits, they are far inferior to those of European Internet companies. China also needs to enact a personal data protection law according to its national conditions.
This thesis applies knowledge graph to the privacy policy research, and analyses Internet companies’ privacy policies from a comparative perspective. It also discusses the comparative results with GDPR and puts forward suggestions, and provides reference for the formulation of China's personal information protection law.