Discovery of the triadic frequent closed patterns based on Hidden Markov Model in folksonomy

With rise of web 2.0, its associated user-centric applications have attracted a lot of users. Folksonomy plays an important role in these systems, which is made of labeling data. Discovery triadic frequent closed patterns is an important tool in knowledge discovery in folksonomy. The huge volume of data and the number of dimensions in these systems, including users, tags and resources are challenging for data mining. In this paper, a method for discovering all triadic frequent closed patterns based on Hidden Markov Model in folksonomy is proposed. By extracting useful data from dataset, the proposed method emprises to build Hidden Markov Model on the two dimensions, then with inference from created hidden model discover triadic frequent closed patterns through applying third dimension on the results. In fact, extracting useful data in the first step and using viterbi based algorithm, for inference, regularly are pruned dataset and are causes for triadic frequent closed patterns to be discovered more quickly. Testing on a real data set taken from "Del.icio.us" website and comparing the results with the same algorithm in the field of folksonomy called "Trias" show that the proposed method in terms of the time, can extract all triadic frequent closed patterns more effectively.