社交网络敏感数据获取方法研究.docx

社交网络敏感数据获取方法研究
摘要:
随着大数据时代的到来,数据变得至关重要,但是数据获取一直是数据挖掘的一个难题。社交网络的成熟使得数据获取变得便捷,但是获取方法仍然有待研究。通过分析社交网络中的信息存储状况,构造了社交网络敏感数据获取模型。从获取用户的个人简介信息中得到用户性别、出生日期、所在地等信息, 并通过浏览记录对用户兴趣进行分析,最后利用好友列表获取其整个社交网中用户的敏感数据。以新浪微博为例研究了用户敏感数据获取率。实验发现,在所有数据获取中职业获取率是最低的,而其它信息获取率较高。
关键词:
社交网络;敏感数据;网络爬虫
DOIDOI:/
中图分类号:TP301
文献标识码:A文章编号文章编号:16727800003005603
英文摘要Abstract:With the advent of the age of big data, the data es critical. But accessing to data has been a problem for data mining. work of mature makes get data convenient, but the method still to be researched. The paper constructed work sensitive data acquisition model by the analysis of work in information storage condition. In the user's personal profile, we get some information such as user gender, date of birth, location, etc., and analyse user interest through the browsing record. Finally we get the entire users sensitive data of work by the list of friends. By python,the paper make web crawler algorithm work sensitive data. In the case of sina weibo , we get users’ sensitive data. In the experiment, we found that the acquisition rate of careers was the lowest, while the other information acquisition rate was higher.
英文关键词Key Words:work; sensitive data; web spider
0引言
社交网络通俗来讲便是人与人交流的不同于现实而依附于虚拟网络存在的人际关系网,如常见的社交平台Facebook、微博、人人网等,但它比现实中人们的关系网更为复杂。随着社交网络的不断发展,网络安全问题变得不可忽视。由于人们对个人隐私数据不重视,使得个人敏感信息泄漏,这种泄漏可能造成的结果可从两个层面分析:①对用户本人而言分两