A major challenge in article clustering is high dimensionality, because this will affect directly to the accuracy. However, it is becoming more important due to the huge textual information available online. In this paper, we proposed an Arabic word net dictionary to extract, select and reduce the features. Additionally, we use the embedding Word2Vector model as feature weighting technique. Finally, for the clustering uses the hierarchy clustering. Our methods are using the Arabic word net dictionary with word embedding, additionally by using the discretization. This method are effective and can enhance improve the accuracy of clustering, which shown in our experimental results.