Artificial intelligence (AI) systems have been constructed as black boxes that cover their internal logic and learning approach from humans, and this has led to several unanswered questions regarding the process and rationale behind AI decisions. Explainable Artificial Intelligence (XAI) is a developing branch of AI that focuses on creating various methods and tools to unbox the inner workings of black-box AI systems. It aims to generate explanations for AI decisions that are easily understood by humans, providing insights and transparency. This paper presented a taxonomy that allows comprehensive categorization of XAI studies. The study aims to illuminate the similarities and differences among various algorithms used in XAI and highlight the characteristics, benefits, and limitations of these algorithms.