Tension is a widespread concern impacting the mental and physical health of individuals, resulting in various health issues. Machine-based learning (ML) has emerged as a favored tool for identifying tension. ML strategies have displayed encouraging outcomes in recognizing trends and attributes from different physiological and behavioral data streams such as heart rate, blood pressure, and vocal signals. The main objective of utilizing ML for tension detection is to offer precise, non-invasive, and economical approaches for early tension identification and intervention. Overall, ML-based tension detection shows substantial potential for delivering an impartial, effective, and expandable strategy for tension monitoring and intervention. Additional exploration is needed to tackle the obstacles linked to data compilation, attribute extraction, and model adaptation to varied populations and scenarios. Keywords: Automated Learning, Simple-minded Bayes, Information, Gloom, Tension.