Social media as a measurement tool of depression in populations

Abstract

Depression is a serious and widespread public health challenge. We examine the potential for leveraging social media postings as a new type of lens in understanding depression in populations. Information gleaned from social media bears potential to complement traditional survey techniques in its ability to provide finer grained measurements over time while radically expanding population sample sizes. We present work on using a crowdsourcing methodology to build a large corpus of postings on Twitter that have been shared by individuals diagnosed with clinical depression. Next, we develop a probabilistic model trained on this corpus to determine if posts could indicate depression. The model leverages signals of social activity, emotion, and language manifested on Twitter. Using the model, we introduce a social media depression index that may serve to characterize levels of depression in populations. Geographical, demographic and seasonal patterns of depression given by the measure confirm psychiatric findings and correlate highly with depression statistics reported by the Centers for Disease

Quantifying Mental Health Signals in Twitter

“…Thus, social media seems like a perfect fit for studying mental health in both individual and overall trends in the population. Such topics have already been the focus of several studies (Coppersmith et al, 2014;De Choudhury et al, 2014;De Choudhury et al, 2013d;De Choudhury et al, 2013b;De Choudhury et al, 2013c;Ayers et al, 2013).…”

“…Work in this area has mostly focused on depression (De Choudhury et al, 2013d;De Choudhury et al, 2013b;De Choudhury et al, 2013c), and the number of users is limited by those that can complete the appropriate survey. For example, De Choudhury et al (2013d) solicited Twitter users to take the CES-D and to share their public Twitter profile, analyzing linguistic and behavioral patterns.…”

Detection of suicide-related posts in Twitter data streams

“…To identify online behaviors that may reflect the mental state of a Twitter user, we established two groups of behavioral features: user-centric and post-centric features [11,28]. User-centric features characterize the behavior of the user in the Twitter community while post-centric features are characteristics that are extracted from the properties of a tweet.…”

“…These features have been shown to carry important information in the context of sentiment analysis [28] and were similarly used by de Choudhury et al [6].…”

A Comprehensive Survey of Time Series Anomaly Detection in Online Social Network Data

“…De Choudhury, S. Checks, and E. Horvitz [8] has presented a work on utilizing a crowdsourcing strategy to [10] has pointed to this investigation were to (1) build a record that deliberate the consciousness of various statistic bunches around schizophrenia-related data on Facebook; (2) consider how this list contrasted crosswise over statistic gatherings and how it corresponded with correlative Web-based (Google Trends) and non-Web-based factors about populace prosperity (emotional well-being markers and framework), and (3) look at the relationship of Facebook determined schizophrenia list with different sorts of online movement and in addition disconnected health and mental health and indicators. K. Garimella, I. Weber, and M. De Choudhury [11] has exactly inspected the part of a recently presented Twitter highlight, 'cite retweets' (or 'quote RTs') in political talk, particularly whether it has prompted enhanced, common, and adjusted trade.…”