We describe the shared task for the CLPsych 2018 workshop, which focused on predicting current and future psychological health from an essay authored in childhood. Language-based predictions of a person’s current health have the potential to supplement traditional psychological assessment such as questionnaires, improving intake risk measurement and monitoring. Predictions of future psychological health can aid with both early detection and the development of preventative care. Research into the mental health trajectory of people, beginning from their childhood, has thus far been an area of little work within the NLP community. This shared task represents one of the first attempts to evaluate the use of early language to predict future health; this has the potential to support a wide variety of clinical health care tasks, from early assessment of lifetime risk for mental health problems, to optimal timing for targeted interventions aimed at both prevention and treatment.

Depression is a global mental health condition that affects all cultures. Despite this, the way depression is expressed varies by culture. Uptake of machine learning technology for diagnosing mental health conditions means that increasingly more depression classifiers are created from online language data. Yet, culture is rarely considered as a factor affecting online language in this literature. This study explores cultural differences in online language data of users with depression. Written language data from 1,593 users with self-reported depression from the online peer support community 7 Cups of Tea was analyzed using the Linguistic Inquiry and Word Count (LIWC), topic modeling, data visualization, and other techniques. We compared the language of users identifying as White, Black or African American, Hispanic or Latino, and Asian or Pacific Islander. Exploratory analyses revealed cross-cultural differences in depression expression in online language data, particularly in relation to emotion expression, cognition, and functioning. The results have important implications for avoiding depression misclassification from machine-driven assessments when used in a clinical setting, and for avoiding inadvertent cultural biases in this line of research more broadly.

In this paper, we provide the first quantified exploration of the structure of the language of dreams, their linguistic style and emotional content. We present a collection of digital dream logs as a viable corpus for the growing study of mental health through the lens of language, complementary to the work done examining more traditional social media. This paper is largely exploratory in nature to lay the groundwork for subsequent research in mental health, rather than optimizing a particular text classification task.

Many psychological phenomena occur in small time windows, measured in minutes or hours. However, most computational linguistic techniques look at data on the order of weeks, months, or years. We explore micropatterns in sequences of messages occurring over a short time window for their prevalence and power for quantifying psychological phenomena, specifically, patterns in affect. We examine affective micropatterns in social media posts from users with anxiety, eating disorders, panic attacks, schizophrenia, suicidality, and matched controls.