Implementation of Text clustering using Genetic Algorithm

Abstract — Text clustering is an important area of interest in the field of Text summarization, sentiment analysis etc. There have been a lot of algorithms experimented during the past years, which have a wide range of performances. One of the most popular method used is k-means, where an initial assumption is made about k, which is the number of clusters to be generated. Now a new method is introduced where the number of clusters is found using a modified spectral bisection and then the output is given to a genetic algorithm where the final solution is obtained