Arabic text mining based on clustering and coreference resolution

Text mining discover and extract useful information from documents, whenever increase the size and number documents leads to redouble features. The huge features for the documents adds challenge to text mining called high dimension. The aim of this proposed study is minimize the high dimension of the documents, and improve Arabic text mining using clustering. In order to achieve this goal, we propose to applied coreference resolution technique using the clustering algorithms k-mediods and k-means. This study uses the similarity metrics Euclidean and Cosine. The system implements using a corpus contains on 200 sport news Arabic. Finally, evaluation measures are used including (Precision' Recall and F-measure) to evaluate our system.