An Efficient Approach for Text Clustering Based on Frequent Itemsets

In recent times, the vast amount of textual information available in electronic form is growing at staggering rate. This increasing number of textual data has led to the task of mining useful or interesting frequent itemsets (words/terms) from very large text databases and still it seems to be quite challenging. The use of such frequent itemsets for text clustering has received a great deal of attention in research community since the mined frequent itemsets reduce the dimensionality of the documents drastically. In the proposed research, we have devised an efficient approach for text clustering based on the frequent itemsets. A renowned method, called Apriori algorithm is used for mining the frequent itemsets. The mined frequent itemsets are then used for obtaining the partition, where the documents are initially clustered without overlapping. Furthermore, the resultant clusters are effectively obtained by grouping the documents within the partition by means of derived keywords. Finally, for experimentation, the Reuter-21578 dataset are used and thus the obtained outputs have ensured that the performance of the proposed approach has been improved effectively.