A Comparative Study of Meta-Heuristic and Conventional Search in Optimization of Multi-Dimensional Feature Selection

Algorithmic – based search approach is ineffective at addressing the problem of multi-dimensional feature selection for document categorization. This study proposes use meta heuristic optimal selection. Elephant optimization (EO) and Ant Colony (ACO) algorithms coupled with Naïve Bayes (NB), Support Vector Machin (SVM), J48 classifiers were used to highlight capability meta-heuristic in In addition, performance results using two approaches (EO ACO) compared conventional Best First Search (BFS) Greedy Stepwise (GS) on news The comparative showed that global subsets attained adaptive parameters tuning scheme. selected number minimized dramatically classification.