An Initiative to Identify Depression using Sentiment Analysis: A Machine Learning Approach

Objective: Online social and news media has turned into an extremely mainstream for clients to impart their insights. The objective of this paper is to propose a methodology through which sentiments can be analyzed. Methods/Statistical analysis: The sentiments are helpful for the identification of the depression. In this paper we proposed an algorithm through which tweets are extracted from twitter using R studio and then their sentiments are analyzed i.e. the scores are given to each sentiment by which we identify whether the person is depressed or not. This gives imperative data to basic leadership in different spaces. Findings: Sentiment analysis over Twitter offers associations and people a quick and powerful approach to screen the general population’s sentiments towards them and their rivals. To evaluate the assumption examination over twitter we need a dataset that is been extracted from the twitter that would be publicly available for twitter sentiment analysis. We found that through twitter to extract tweets are scored based on their sentiments. The result is unique as we have proposed new algorithm through which twitter sentiments are scored. Applications: This sentiment analysis will be helpful to draw conclusion, whether the person is depressed or not. It can be helpful for prescreening test, diagnostic tool and automation monitoring system.