Abstract: In the contemporary era, people are moving towards the achievement of ‘goals’ as dictated by society and in the process, they often overlook their emotional and psychological health. There are quite a few health issues that society has been trying to address, the most concerning being psychological issues – depression, stress, etc. Failing to treat these issues can then lead to a range of mental health illnesses, for example, someone with bipolar disorder, which can lend up to be heart-wrenching. In order to mitigate the extent of these occurrences, it is critical to find and treat the affected areas promptly. This research aims to develop a model using machine learning that will be able to detect indications of despondency – the feeling of hopelessness. Working professionals were the subjects and given an array of questions through which depressive characteristics could be detected. A variety of machine learning methodologies were used to assess and categorize the information. A Random Forest algorithm delivered the best result among them, with an 87.02% accuracy rate and better precision and dependability than other approaches. Many conclusions were reached as a result of the study, the most striking being how machine learning can be used to detect any patterns to mental health illnesses, thus detection could potentially be quicker. In harnessing such data-oriented strategies, this paper provides an instrument that is easy to implement and can be used at scale for assessing mental well-being.
Keywords: depression detection, bipolar disorder, stress analysis, Random Forest algorithm, despondency detection, working professionals, predictive modelling , dataset analysis, mental health assessment.
Copyright Form