Predicting postpartum changes in emotion and behavior via social media

Abstract

We consider social media as a promising tool for public health, focusing on the use of Twitter posts to build predictive models about the influence of childbirth on the forthcoming behavior and mood of new mothers. Using Twitter posts, we quantify postpartum changes in 376 mothers along dimensions of social engagement, emotion, social network, and linguistic style. We then construct statistical models from a training set of observations of these measures before and after the reported childbirth, to forecast significant postpartum changes in mothers. The predictive models can classify mothers who will change significantly following childbirth with an accuracy of 71%, using observations about their prenatal behavior, and as accurately as 80-83% when additionally leveraging the initial 2-3 weeks of postnatal data. The study is motivated by the opportunity to use social media to identify mothers at risk of postpartum depression, an underreported health concern among large populations, and to inform the design of low-cost, privacy-sensitive early-warning systems and intervention programs aimed at promoting wellness postpartum.

Natural language processing in mental health applications using non-clinical texts

“…An understudied area is that of real use triage systems, used 'in the wild,' where individuals considered 'at risk' are identified in order to receive some form of assistance. We have already discussed studies by Choudhury and others who used Twitter (De Choudhury et al 2013a) and Facebook (De Choudhury and Counts 2014) data and where recent mothers at risk of depression were identified, yet these studies did not evaluate how those people could be offered assistance, or whether this would even be acceptable.…”

Potentials of Using the Narrative as a Diagnostic Tool for the Study of Parental Attitude

“…Было обнаружено, что ма-тери, склонные к экстремальным нега-тивным изменениям поведения, харак-терным для послеродовой депрессии, в период первого месяца после родов, демонстрируют снижение объёма по-стов на интернет-ресурсе (в Твиттере), а также возникновение заметного не-гативного эмоционального выражения переживаний. Кроме того, лингвисти-ческий стиль постов таких матерей характеризовался наличием высокого фокуса внимания к самим себе и сво-им тяжелым переживаниям, что могло существенным образом сказаться на их родительском отношении [8].…”

Conceptualizing the self: A critical analysis of the self as a discursive trend in human-computer interaction research

“…For example, De Choudhury, Counts, and Horvitz (2013), in an effort to understand the connection between online posting and postpartum depression, statistically analyzed patterns of posting, linguistic style, and emotional expression in Twitter posts made by 376 women. Rather than only focusing on identifying explicit references to depression, the authors argued that it is possible to identify indirect markers, that is, linguistic style and frequency of posting, in the Twitter texts.…”

“…Even in research on the communicative self, the self is described as ontologically separated from other people. Some of the researchers in this analysis portrayed the communicative process in terms of a simple process of transmitting information (e.g., De Choudhury et al, 2013;Hancock et al, 2007;Ozenc & Farnham, 2011;Raban et al, 2012;C. Zhao & Jiang, 2011).…”