Abstract: Web has become an important information source for most people. However, the information on the web is not always true and credible. How to help people quickly judge the credibility of information on the web was required. A new method based on content trust was proposed in this paper, which aim to evaluate the credibility of web information. Firstly, the method utilized the conditional random field model to get the theme of web information content, which can be used to a clue to collect the candidate evidence on the web. Secondly, the truthfulness of evidence can be evaluated by the characteristic of the concurrency and relevancy of the evidence and web information theme and other characteristic. Finally, the credibility value of web information was calculated. The experiment results show the method proposed in the credibility evaluation of web information content is reasonable and effective.