• L.Greeshma
• M.Jahnavi Rao
• Dr. R. Jegadeesan
• M.Sindhu
• Y.Chandralekha Rao

With the movement of life online, an impressive number of individuals routinely give their behaviors, inclinations and well-ordered battles with mental success problems through methods for electronic media frames in the media stages of the organization such as Twitter. In no way, as the standard observer-observer evaluators conducted through self-developed surveys and surveys, did we investigate the reliable revelation of the clinical misery of subtly collected tweets. In the context of the examination of tweets from clients with problematic autodemolent signs in their Twitter profiles, we show the potential to see clinical sadness responses that duplicate the PHQ-9 scheme currently used by physicians. Our survey uses a genuine semi-guided model to study how the reach of these signs and their appearance on Twitter (the extent to which wordplans and topical propensities) are aligned with point-by-point support revelations using techniques for the PHQ-9. Our proactive and adjusted detection instrument can perceive problematic clinical responses with an accuracy of 68% and a precision of 72%.

Semi-supervised Machine Learning, Natural Language Processing, Social Media, Mental Health

"PUBLIC HEALTH MONITORING ON SOCIAL NETWORS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.202-207, March-2019, Available :http://www.jetir.org/papers/JETIRAU06030.pdf

"PUBLIC HEALTH MONITORING ON SOCIAL NETWORS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp202-207, March-2019, Available at : http://www.jetir.org/papers/JETIRAU06030.pdf