請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60604
標題: | 社群網路之用戶隱私資料推知技術 User Profile Data Inference for Online Social Network |
作者: | Chih-Hsien Yeh 葉治顯 |
指導教授: | 逄愛君(Ai-Chun Pang) |
關鍵字: | 社群網路,推知,貝式定理, Social Network,Inference,Bayesian Theorem, |
出版年 : | 2013 |
學位: | 碩士 |
摘要: | Currently, online social networks (OSNs) have become one of the most popular web
services. Billions of people share personal information and build social relations with others. Many service providers are interested in users' living areas for improving their quality of service. To gather users' living areas, one possible solution is to collect infor- mation of living areas from OSNs. Unfortunately, most of the users don't want to share this information to the public. An inference technique is needed for these service providers in order to develop these applications. In this thesis, we investigate and apply several methods including most-frequent, bayesian, and support vector machine (SVM) algorithms to infer users' living areas. An iterative algorithm is designed and implemented to infer user living area information while considering users' inclination to conceal personal data. We con- ducted our experiment by applying our method to a real world dataset, and the inference accuracy of the proposed method is (over than) 60%, which is much higher compared to non-iterative methods (13%). |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/60604 |
全文授權: | 有償授權 |
顯示於系所單位: | 資訊網路與多媒體研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-102-1.pdf 目前未授權公開取用 | 1.74 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。