A novel metaheuristic optimisation approach for text sentiment analysis

Abstract Automated sentiment analysis is considered an area in natural language processing research that seeks to understand a text author's mood, thoughts, and feelings. New opportunities challenges have arisen this field due the popularity accessibility of variety resources ideas, such as online review websites, personal blogs, social media. Feature selection, which can be conducted using metaheuristic algorithms, one steps analysis. It crucial use high-performing algorithms for feature selection. This paper applies Horse herd Optimisation Algorithm (HOA) selection HOA algorithm uses six key behaviours simulate performance horses various ages, solve high-dimensional optimisation problems. In order improve HOA, adds another behaviour basic algorithm; thus, new seven different ages imitate their performance. then discretised converted multi-objective algorithm. The improved algorithm's evaluated 15 CEC benchmark functions, results are compared Binary Social Spider Algorithm, Grey Wolf Optimizer, Butterfly Optimization Algorithm. algorithm, Multi-objective (MBHOA), excels at solving complex To evaluate practical example, it employed examined on data sets. simulation indicate MBHOA has better analysing similar approaches.