Online social networks are now recognized as an important platform for the spread of information. While providing convenient exchange for users

it also makes OSNs fertile grounds for the wide spread of misinformation which can lead to undesirable consequences.Most mainstream media outlets use keyword matching as a search method to find misinformation and forbid the presentation in context.However

this method also blocks positive messages related to misinformation.In this paper

we propose an adaptive opinion guiding model to limit the spread of misinformation.Based on user's opinion and sentiment

the model recommends messages or other users that have relative positive feeling to current user.It also introduces the feedback mechanism to achieve a long-term and accurate guiding by adjusting the pushing content dynamically.We also design and finish the guiding system.Experiments show that the model can guide the opinion of the network group effectively.