English Dictionary

For co-clustering the web documents data, existing algorithms have three challenges, they are: meta-information that are available is usually precise so that the extracted tags or the categories cannot be adequatively weighted by conventional data mining routine such as term frequencyinverse document frequency (tf-idf). Next the feature vectors weight in the function depends on various experimental settings lead to unsounded conclusion. Finally, there is high computational overhead for ensuring the concurrence which requires a repeating process.