面向网络文本的信息可信度评估方法研究

Research on Information Credibility based on Web Text

随着网络信息的膨胀性增长,不可信的信息在网络中日益增多,阻碍误导用户对可信信息的获取。研究网络文本的可信度评估方法,对句子级命题提取多维网络分布特征,通过线性组合计算可信度值,从而判断命题的可信度。在可信度评估过程中,文中方法通过词语结构特征提取可信信息的候选信息,并在候选信息的可信度计算中加入对信息源的可信度分析判断,提高了信息可信度的评估准确度。

With the rapid growth of the network information, there are more and more untrusted information which mislead people to get the truth. The paper makes a research on the credibility of the web text information, and extracts the muhidimensional network distribution features at the sentence - level , therefore evaluates the value of credibility by linear model. In the processing of information Credibility evaluating, the paper also makes the evaluation of the credibility of the information source, and improves the degree of accuracy.