The paper "Predicting Depression via Social Media" by Munmun De Choudhury, Michael Gamon, Scott Counts, and Eric Horvitz explores the potential of using social media to detect and diagnose major depressive disorder (MDD). The authors use crowdsourcing to compile a set of Twitter users diagnosed with clinical depression based on the CES-D screening test. They measure various behavioral attributes, including social engagement, emotion, language, linguistic styles, ego network, and mentions of antidepressant medications, over a year before the onset of depression. These signals are used to build a statistical classifier that predicts the risk of depression before its onset, achieving an accuracy of 70% and precision of 0.74. The study finds that social media posts can provide useful signals for characterizing the onset of depression, such as decreased social activity, increased negative affect, highly clustered ego networks, heightened relational and medicinal concerns, and greater expression of religious involvement. The findings suggest that social media can be a valuable tool for identifying individuals at risk of depression, potentially complementing traditional diagnostic methods.The paper "Predicting Depression via Social Media" by Munmun De Choudhury, Michael Gamon, Scott Counts, and Eric Horvitz explores the potential of using social media to detect and diagnose major depressive disorder (MDD). The authors use crowdsourcing to compile a set of Twitter users diagnosed with clinical depression based on the CES-D screening test. They measure various behavioral attributes, including social engagement, emotion, language, linguistic styles, ego network, and mentions of antidepressant medications, over a year before the onset of depression. These signals are used to build a statistical classifier that predicts the risk of depression before its onset, achieving an accuracy of 70% and precision of 0.74. The study finds that social media posts can provide useful signals for characterizing the onset of depression, such as decreased social activity, increased negative affect, highly clustered ego networks, heightened relational and medicinal concerns, and greater expression of religious involvement. The findings suggest that social media can be a valuable tool for identifying individuals at risk of depression, potentially complementing traditional diagnostic methods.