Approach to SOM based correlation clustering

Correlation clustering problem is a NP hard problem and an approach based on self organizing feature map (SOM) neural network for correlation clustering is presented in this paper. Clustering performance of SOM neural network based correlation clustering is test with 20 newsgroups data in UCI KDD archive. Experimental results show that the performance of clustering division constructed by correlation clustering based on SOM neural network is better with clustering precision as criterion meanwhile the time complexity of correlation clustering based on SOM neural network is better too.