Small but Mighty: Affective Micropatterns for Quantifying Mental Health from Social Media Language

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.

[1]  Mark Dredze,et al.  Ethical Research Protocols for Social Media Health Research , 2017, EthNLP@EACL.

[2]  Maarten Sap,et al.  Mental Illness Detection at the World Well-Being Project for the CLPsych 2015 Shared Task , 2015, CLPsych@HLT-NAACL.

[3]  Glen Coppersmith,et al.  Exploratory Analysis of Social Media Prior to a Suicide Attempt , 2016, CLPsych@HLT-NAACL.

[4]  Mark Dredze,et al.  Detecting Changes in Suicide Content Manifested in Social Media Following Celebrity Suicides , 2015, HT.

[5]  J. Gross,et al.  Depression and emotional reactivity: variation among Asian Americans of East Asian descent and European Americans. , 2007, Journal of abnormal psychology.

[6]  Cindy K. Chung,et al.  The Psychological Functions of Function Words , 2007 .

[7]  Eric Horvitz,et al.  Predicting Depression via Social Media , 2013, ICWSM.

[8]  Evan M. Kleiman,et al.  Risk Factors for Suicidal Thoughts and Behaviors: A Meta-Analysis of 50 Years of Research , 2017, Psychological bulletin.

[9]  L. Kruisselbrink,et al.  The Neurocognitive Effects of Alcohol Hangover: Patterns of Impairment/Nonimpairment Within the Neurocognitive Domains of the Diagnostic and Statistical Manual of Mental Disorders, 5th Edition , 2019, Neuroscience of Alcohol.

[10]  Y. Bar-Haim,et al.  Threat-related attentional bias in anxious and nonanxious individuals: a meta-analytic study. , 2007, Psychological bulletin.

[11]  M. Adler Diagnostic and Statistical Manual of Mental Disorders, 4th Edition , 2016 .

[12]  Minsu Park,et al.  Depressive Moods of Users Portrayed in Twitter , 2012 .

[13]  Mark Dredze,et al.  Discovering Shifts to Suicidal Ideation from Mental Health Content in Social Media , 2016, CHI.

[14]  Maarten Sap,et al.  Developing Age and Gender Predictive Lexica over Social Media , 2014, EMNLP.

[15]  J. Rosmalen,et al.  How to assess stress biomarkers for idiographic research? , 2015, Psychoneuroendocrinology.

[16]  Cheri A. Levinson,et al.  Facebook Use and Disordered Eating in College-Aged Women. , 2015, The Journal of adolescent health : official publication of the Society for Adolescent Medicine.

[17]  Mike Conway,et al.  Ethical issues in using Twitter for population-level depression monitoring: a qualitative study , 2016, BMC Medical Ethics.

[18]  Jim van Os,et al.  Redeeming diagnosis in psychiatry: timing versus specificity , 2013, The Lancet.

[19]  Glen Coppersmith,et al.  Quantifying the Language of Schizophrenia in Social Media , 2015, CLPsych@HLT-NAACL.

[20]  Glen A. Coppersmith,et al.  Quantifying Suicidal Ideation via Language Usage on Social Media , 2015 .

[21]  Eric Gilbert,et al.  VADER: A Parsimonious Rule-Based Model for Sentiment Analysis of Social Media Text , 2014, ICWSM.

[22]  Thomas R Insel,et al.  Translating scientific opportunity into public health impact: a strategic plan for research on mental illness. , 2009, Archives of general psychiatry.

[23]  Ted Pedersen,et al.  Screening Twitter Users for Depression and PTSD with Lexical Decision Lists , 2015, CLPsych@HLT-NAACL.

[24]  Munmun De Choudhury,et al.  Happy, Nervous or Surprised? Classification of Human Affective States in Social Media , 2012, ICWSM.

[25]  M. Rudd,et al.  Fluid Vulnerability Theory: A Cognitive Approach to Understanding the Process of Acute and Chronic Suicide Risk. , 2006 .

[26]  J. van Os,et al.  The dynamics of subthreshold psychopathology: implications for diagnosis and treatment. , 2013, The American journal of psychiatry.

[27]  Mark Dredze,et al.  Measuring Post Traumatic Stress Disorder in Twitter , 2014, ICWSM.

[28]  M. Wichers,et al.  Moving From Static to Dynamic Models of the Onset of Mental Disorder: A Review , 2017, JAMA psychiatry.

[29]  Daniel Antonius,et al.  Avolition and expressive deficits capture negative symptom phenomenology: implications for DSM-5 and schizophrenia research. , 2011, Clinical psychology review.

[30]  Thang Nguyen,et al.  The University of Maryland CLPsych 2015 Shared Task System , 2015, CLPsych@HLT-NAACL.

[31]  Mark Dredze,et al.  Quantifying Mental Health Signals in Twitter , 2014, CLPsych@ACL.

[32]  Christopher M. Danforth,et al.  Forecasting the onset and course of mental illness with Twitter data , 2016, Scientific Reports.

[33]  Mark Dredze,et al.  Shared Task : Depression and PTSD on Twitter , 2015 .

[34]  Mark Dredze,et al.  From ADHD to SAD: Analyzing the Language of Mental Health on Twitter through Self-Reported Diagnoses , 2015, CLPsych@HLT-NAACL.

[35]  Munmun De Choudhury,et al.  Recovery Amid Pro-Anorexia: Analysis of Recovery in Social Media , 2016, CHI.

[36]  Shekhar Saxena,et al.  World Health Organization's Comprehensive Mental Health Action Plan 2013–2020 , 2014, Psychiatry and clinical neurosciences.

[37]  R. Atun,et al.  Estimating the true global burden of mental illness. , 2016, The lancet. Psychiatry.

[38]  Andree E. Rose,et al.  Predictors of Emerging Suicide Death Among Military Personnel on Social Media Networks , 2018, Suicide & life-threatening behavior.