Abstarct: This thesis investigates the optimization of market sentiment analysis in the Forex market baxsed on evolutionary algorithms. The Forex market, as the largest and most active financial market in the world, provides traders with advanced tools and modern technologies for conducting trades. One of these tools is algorithmic trading, which utilizes complex algorithms and specific programming to execute trades automatically. The main objective of this study is to design a system with optimized trading strategies that can offer superior performance in the Forex market. This system is designed to leverage market sentiment analysis capabilities and is optimized using evolutionary algorithms. In this regard, the Shuffled Frog Leaping Algorithm (SFLA) and Particle Swarm Optimization (PSO) are used as optimization tools to improve the performance of the trading strategy. The proposed trading strategy for the XAU/USD currency pair is baxsed on the Supertrend indicator and market sentiment, optimized by the SFLA and PSO algorithms. The foundation of this strategy is the ratio of buyers to sellers in the market, which is optimized by the aforementioned algorithms. These algorithms aid in extracting optimal parameters for trading strategies by analyzing historical data and evaluating trader behavior in the market, thereby enhancing the overall performance of the system. Experiments were conducted on one-minute data for the XAU/USD currency pair over a specific period. The results indicate that this optimized strategy has been profitable, with the profit from trades using the PSO optimization method amounting to 506.06, and the profit using the SFLA optimization method amounting to 479.07. The use of optimization algorithms significantly accelerates the process of finding suitable parameters for trades, which is crucial in time-sensitive trading environments like Forex. In summary, this study demonstrates that combining the Supertrend indicator and market sentiment with optimization algorithms such as SFLA and PSO can lead to the development of an efficient and profitable trading strategy in the Forex market. These results highlight the high potential of utilizing evolutionary optimization methods to enhance the performance of trading strategies in financial markets.