Email spam detection is very necessary to maintain the integrity of the communication channel in today’s digital world. Spam strategies have become more sophisticated nowadays and traditional spam detection techniques often struggle to keep up. This paper explores a spam detection method containing different machine learning algorithms. In order to achieve this, the authors used a well selected dataset taken from Kaggle, having tweets that were legitimately categorized as ‘spam’ or ‘ham’. This paper completes technique including complex data pre-processing along with sentiment analysis, tokenization, and text normalization. Furthermore, thorough exploratory data analysis provided insightful information on the patterns of distribution of both spam and amateur emails. Different algorithms like KNN, Linear Regression, Decision tree, Naïve Bayes, and SVM have been used to find the efficiency of the Spam detection. Never-ending search for the best spam detection algorithm has led the authors to conduct a thorough review procedure including a number of crucial metrics such as precision, accuracy, recall, and F1 score that ultimately gave the optimal solution with the overall goal of this work. In conclusion, this work led to the analyse the preference of an email spam detection system that can quickly identify emails as ‘spam’ or ‘ham’.