Wrapper and Hybrid Feature Selection Methods Using Metaheuristic Algorithms for English Text Classification: A Systematic Review

Feature selection (FS) constitutes a series of processes used to decide which relevant features/attributes include and irrelevant features exclude for predictive modeling. It is crucial task that aids machine learning classifiers in reducing error rates, computation time, overfitting, improving classification accuracy. has demonstrated its efficacy myriads domains, ranging from use text (TC), mining, image recognition. While there are many traditional FS methods, recent research efforts have been devoted applying metaheuristic algorithms as techniques the TC task. However, few literature reviews concerning TC. Therefore, comprehensive overview was systematically studied by exploring available studies different improve This paper will contribute body existing knowledge answering four questions (RQs): 1) What approaches apply TC? 2) Does lead better accuracy than typical methods? 3) How effective modified, hybridized problems?, 4) gaps current their future directions? These RQs led study works on metaheuristic-based contributions, limitations. Hence, final list thirty-seven (37) related articles extracted investigated align with our generate new domain study. Most conducted papers focused addressing tandem based wrapper hybrid approaches. Future should focus using hybrid-based approach it intuitively handles complex optimization problems potentiality provide opportunities this rapidly developing field.