Characterizing Sleep Issues Using Twitter

Background Sleep issues such as insomnia affect over 50 million Americans and can lead to serious health problems, including depression and obesity, and can increase risk of injury. Social media platforms such as Twitter offer exciting potential for their use in studying and identifying both diseases and social phenomenon. Objective Our aim was to determine whether social media can be used as a method to conduct research focusing on sleep issues. Methods Twitter posts were collected and curated to determine whether a user exhibited signs of sleep issues based on the presence of several keywords in tweets such as insomnia, “can’t sleep”, Ambien, and others. Users whose tweets contain any of the keywords were designated as having self-identified sleep issues (sleep group). Users who did not have self-identified sleep issues (non-sleep group) were selected from tweets that did not contain pre-defined words or phrases used as a proxy for sleep issues. Results User data such as number of tweets, friends, followers, and location were collected, as well as the time and date of tweets. Additionally, the sentiment of each tweet and average sentiment of each user were determined to investigate differences between non-sleep and sleep groups. It was found that sleep group users were significantly less active on Twitter (P=.04), had fewer friends (P<.001), and fewer followers (P<.001) compared to others, after adjusting for the length of time each user's account has been active. Sleep group users were more active during typical sleeping hours than others, which may suggest they were having difficulty sleeping. Sleep group users also had significantly lower sentiment in their tweets (P<.001), indicating a possible relationship between sleep and pyschosocial issues. Conclusions We have demonstrated a novel method for studying sleep issues that allows for fast, cost-effective, and customizable data to be gathered.

[1]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[2]  Ulrich Voderholzer,et al.  Primary insomnia: a risk factor to develop depression? , 2003, Journal of affective disorders.

[3]  M. Fava.  Daytime sleepiness and insomnia as correlates of depression. , 2004, The Journal of clinical psychiatry.

[4]  Alex Gamma,et al.  Prevalence, course, and comorbidity of insomnia and depression in young adults. , 2008, Sleep.

[5]  Daniel J. Taylor.  Insomnia and depression. , 2008, Sleep.

[6]  M. Peterson,et al.  Insomnia and depression. , 2008, Sleep medicine.

[7]  G. Eysenbach.  Infodemiology and Infoveillance: Framework for an Emerging Set of Public Health Informatics Methods to Analyze Search, Communication and Publication Behavior on the Internet , 2009, Journal of medical Internet research.

[8]  Scott A. Golder,et al.  Diurnal and Seasonal Mood Vary with Work, Sleep, and Daylength Across Diverse Cultures , 2011 .

[9]  J. Brownstein,et al.  Social and news media enable estimation of epidemiological patterns early in the 2010 Haitian cholera outbreak. , 2012, The American journal of tropical medicine and hygiene.

[10]  Sue Jamison-Powell,et al.  "I can't get no sleep": discussing #insomnia on twitter , 2012, CHI.

[11]  Eric Horvitz,et al.  Social media as a measurement tool of depression in populations , 2013, WebSci.

[12]  J. Carroll,et al.  A New Dimension of Health Care: Systematic Review of the Uses, Benefits, and Limitations of Social Media for Health Communication , 2013, Journal of medical Internet research.

[13]  D. Chapman,et al.  Frequent insufficient sleep and anxiety and depressive disorders among U.S. community dwellers in 20 states, 2010. , 2013, Psychiatric services.

[14]  J. Brownstein,et al.  Assessing the Online Social Environment for Surveillance of Obesity Prevalence , 2013, PloS one.

[15]  Scott H. Burton,et al.  An Exploration of Social Circles and Prescription Drug Abuse Through Twitter , 2013, Journal of medical Internet research.

[16]  T. Strine,et al.  Association between perceived insufficient sleep, frequent mental distress, obesity and chronic diseases among US adults, 2009 behavioral risk factor surveillance system , 2013, BMC Public Health.

[17]  Björn W. Schuller,et al.  New Avenues in Opinion Mining and Sentiment Analysis , 2013, IEEE Intelligent Systems.

[18]  Michael J. Paul,et al.  Discovering Health Topics in Social Media Using Topic Models , 2014, PloS one.

[19]  P Staccini,et al.  Social media and patient health outcomes. Findings from the yearbook 2014 section on consumer health informatics. , 2014, Yearbook of medical informatics.

[20]  W. Orr,et al.  Predictors and patterns of insomnia symptoms in OSA before and after PAP therapy. , 2014, Sleep medicine.

[21]  N. Vozoris.  Insomnia symptom frequency and hypertension risk: a population-based study. , 2014, The Journal of clinical psychiatry.

[22]  Ara Darzi,et al.  Tweets about hospital quality: a mixed methods study , 2014, BMJ quality & safety.

[23]  S. Øverland,et al.  Midlife insomnia and subsequent mortality: the Hordaland health study , 2014, BMC Public Health.

[24]  A. Acquisti,et al.  Reputation as a sufficient condition for data quality on Amazon Mechanical Turk , 2013, Behavior Research Methods.

[25]  Adam D. I. Kramer,et al.  Detecting Emotional Contagion in Massive Social Networks , 2014, PloS one.

[26]  E. Nsoesie,et al.  Guess Who’s Not Coming to Dinner? Evaluating Online Restaurant Reservations for Disease Surveillance , 2014, Journal of medical Internet research.

[27]  Kristin L. Schneider,et al.  Tweeting it off: characteristics of adults who tweet about a weight loss attempt , 2014, J. Am. Medical Informatics Assoc..

[28]  H. Sueki,et al.  The association of suicide-related Twitter use with suicidal behaviour: a cross-sectional study of young internet users in Japan. , 2015, Journal of affective disorders.