A model for evaluating the quality of user-created documents

摘要: In this paper, we propose a model for evaluating the quality of general user-created documents. The is based on supervised classification approach, in which output scores are considered as given document. order to utilize both textual and nontextual attributes documents, incorporated number objectively measurable, real-valued features selected upon predefined criteria quality. Experiments two datasets real world documents show that stable indicators documents' Some inferred be effective kinds