Due to the extensive usage of the Internet, social media has grown to play a significant role in our daily lives. Twitter is one of the most popular social media platforms in use today. People express their ideas through tweets on a variety of topics, including politics, sports, the economy, and more. The massive dataset produced by the daily millions of tweets caught the interest of data scientists, who decided to concentrate on it for sentiment analysis. This research propose novel technique in machine learning algorithm in big data for social media based sentimental analysis. Here the input data has been collected as social media based sentimental data and processed for noise removal. Then this data has been clustered using Fuzzy-C means clustering and feature extracted using differential multi-layer whale optimization. The experimental analysis has been carried out in terms of accuracy, precision, recall, AUC and RMSE. The proposed technique attained accuracy of 95%, precision of 72%, recall of 62%, AUC of 44%, RMSE of 52%.