摘要
随着互联网的发展,社交网络在人们的工作生活中扮演着重要的角色,人们在社交网络中发布、分享信息和观点,这些社交行为产生大量的数据,使得社交网络成为蕴含个人信息和情感的载体。该课题在已有相关研究的基础上,提出并验证了一种根据用户社交网络数据对用户的人格倾向进行预测的方法。在实现过程中,利用爬虫技术得到微博用户的相关数据,其中包括用户在使用社交网络时产生的文本信息,以及用户的行为信息与社交关系信息,工作重点是通过提取采集数据信息的相关特征值,并对特征值进行降维处理,在建立预测模型时采用了机器学习方法以提高准确率。通过对比实验,验证了提出的预测方法在人格预测的精确度上有显著的提高。
With the development of the Internet, the social networks start playing an important role in people＇s work and life. Peo-ple publish and share information and opinions in social networks, and thus generate a large amount of data, making social net-works a carrier of personal information and emotion. Based on the existing studies, this research proposes a method to predict per-sonality tendency in the light of social network data. In the process of implementation, we use crawler technology to get the relateddata of micro-blog users, including the text information generated by users when using social networks, as well as their behavior in-formation and social relationship information. The focus lies in extracting the relevant characteristics of the collected data and infor-mation and reducing the dimension of the eigenvalue. A machine learning method is adopted in the process of establishing the fore-casting model to improve the accuracy. Through comparative experiments, it is verified that the proposed prediction method pres-ents a significant improvement in the accuracy of personality prediction.
作者
娜迪热
胡俊
NA Di-re, HU Jun （School of Computer Science and Technology, BeiJing Jiao Tong University, BeiJing 10044, China ）
出处
《电脑知识与技术》
2018年第3期6-11,共6页
Computer Knowledge and Technology
关键词
社交网络
特征抽取
机器学习
人格倾向性分析
Social Network
Feature Extraction
Machine Learning
Personality Propensity Analysis
