Lately, we have seen the problem of sparsity data has increased due to the increase in the amount of available documentation on the Internet, to take care of this issue need to choose the best strategy for the representation of the content. In recent years, scientists have been switched to the representation of the content graphically. Because the results of previous studies proved that the represented data as graphs reduce the problem of sparse data. So this study aims to review the sorts of graphs used to represent the content of documents. Were the exploratory outcomes recommended that our methodologies are superior to other methodologies in each of the synthetic global data sets and the real.