中文摘要：

社交媒体中的个性化推荐试图通过对公开在公众平台中的用户位置、图片等信息的分析得到用户的习惯、性格等，以提供个性化服务，但也因此给用户的隐私安全造成威胁。从隐私挖掘的角度，提出了一种基于人物图像的人物性格隐私分析方法。基于认知科学中的人物性格模型，提出了5类视觉特征，包括颜色、纹理、形状、伊顿对比和表情特征。实验表明，所提方法可以有效挖掘用户的性格隐私，特征选择实验进一步验证了所提出特征的有效性。

英文摘要：

Personalized recommendation in social media attempts to analyze the habits and personality based on the location information and pictures from the users＇ comments on the public platform. This is very useful for personalized information recommendation. But from perspective of privacy protection, this will affect the privacy security. A novel human personality privacy analysis method based on portrait was proposed. By analyzing the personality model of the psy- chology, five visual features were proposed, including color features, texture features, shape features, Itten contrast features and expression features. Comprehensive experiments demonstrate the effectiveness of the proposed method. Further, the features analysis experiment show that the proposed features are very relevant to human personality privacy analyzing.