Hi..does anyone know about FTC algorithm (Frequent Term-Based Text Clustering) ?
i have a difficulty to cluster the terms..
thanks so much

this is the algorithm :

FTC(database D, float minsup)
SelectedTermSets:= {};
n:= |D|;

RemainingTermSets:= DetermineFrequentTermsets(D, minsup);

while |cov(SelectedTermSets)| ‚ n do
  for each set in RemainingTermSets do
    Calculate overlap for set;

  BestCandidate:=element of RemainingTermSets with minimum overlap;
  SelectedTermSets:= SelectedTermSets ¾ {BestCandidate};
  RemainingTermSets:= RemainingTermSets -{BestCandidate};
  Remove all documents in cov(BestCandidate) from D and from the coverage of all of the
  RemainingTermSets;

return SelectedTermSets and the cover of the elements of SelectedTermSets;

Well... I dunno. I'm amateur in Java programming