A novel hybrid multi-verse optimizer with K-means for text documents clustering

摘要

Text clustering has been widely utilized with the aim of partitioning specific document collection into different subsets using homogeneity/heterogeneity criteria. It has also become a very complicated area of research, including pattern recognition, information retrieval, and text mining. Metaheuristics are typically used as efficient approaches for the text clustering problem. The multi-verse optimizer algorithm (MVO) involves a stochastic population-based algorithm. It has been recently proposed and successfully utilized to tackle many hard optimization problems. However, a recently applied research trend involves hybridizing two or more algorithms with the aim of obtaining a superior solution regarding the problems of optimization. In this paper, a new hybrid of MVO algorithm with the K-means clustering algorithm is proposed, i.e., the H-MVO algorithm with the aims of enhancing the quality of initial candidate solutions, as well as the best solution, which is produced by MVO at each iteration. This hybrid algorithm aims at improving the global (diversification) ability of the search and finding a better cluster partition. The proposed H-MVO effectiveness was tested on five standard datasets, which are used in the domain of data clustering, as well as six standard text datasets, which are utilized in the domain of text document clustering, in addition to two scientific articles' datasets. The experiments showed that K-means hybridized MVO improves the results in terms of high convergence rate, accuracy, error rate, purity, entropy, recall, precision, and F-measure criteria. In general, H-MVO has outperformed or at least proven to be highly competitive compared to the original MVO algorithm and with well-known optimization algorithms like KHA, HS, PSO, GA, H-PSO, and H-GA and the clustering techniques like K-mean, K-mean++, DBSCAN, agglomerative, and spectral clustering techniques.