The increasing popularity of nature-inspired meta-heuristic algorithms in real-world optimization problems has been attributed to their advantages over traditional numerical optimization techniques. This study introduces the Whale Swarm Algorithm (WSA), a nature-inspired meta-heuristic, which draws inspiration from whales' communication through ultrasound for hunting. The focus of this paper is on using WSA for feature optimization. Text mining finds applications in various domains, such as business intelligence, social media analysis, sentiment analysis, biomedical analysis, software process analysis, and security analysis. This paper explores the use of WSA as an optimization algorithm, particularly in automating the understanding of Arabic text and constructing ontologies. Additionally, the paper delves into the challenges faced in enhancing the WSA models. Furthermore, this research presents a comprehensive overview of the diverse applications of WSA in different fields, with a specific emphasis on its role in ontology learning from Arabic text, aiming to improve swarm optimization techniques in practical use cases.