Chandler McClellan1, Mir M Ali1, Ryan Mutter1, Larry Kroutil2, Justin Landwehr2. 1. Center for Behavioral Health Statistics and Quality, Substance Abuse and Mental Health Services Administration, Rockville, Maryland, USA. 2. Behavioral Health and Criminal Justice Division, Social, Statistical, and Environmental Sciences, RTI International, Research Triangle Park, North Carolina, USA.
Abstract
OBJECTIVES: Given the public health importance of communicating about mental illness and the growing use of social media to convey information, our goal was to develop an empirical model to identify periods of heightened interest in mental health topics on Twitter. MATERIALS AND METHODS: We collected data on 176 million tweets from 2011 to 2014 with content related to depression or suicide. Using an autoregressive integrated moving average (ARIMA) data analysis, we identified deviations from predicted trends in communication about depression and suicide. RESULTS: Two types of heightened Twitter activity regarding depression or suicide were identified in 2014: expected increases in response to planned behavioral health events, and unexpected increases in response to unanticipated events. Tweet volume following expected increases went back to the predicted level more rapidly than the volume following unexpected events. DISCUSSION: Although ARIMA models have been used extensively in other fields, they have not been used widely in public health. Our findings indicate that our ARIMA model is valid for identifying periods of heightened activity on Twitter related to behavioral health. The model offers an objective and empirically based measure to identify periods of greater interest for timing the dissemination of credible information related to mental health. CONCLUSION: Spikes in tweet volume following a behavioral health event often last for less than 2 days. Individuals and organizations that want to disseminate behavioral health messages on Twitter in response to heightened periods of interest need to take this limited time frame into account. Published by Oxford University Press on behalf of the American Medical Informatics Association 2016. This work is written by US Government employees and is in the public domain in the United States.
OBJECTIVES: Given the public health importance of communicating about mental illness and the growing use of social media to convey information, our goal was to develop an empirical model to identify periods of heightened interest in mental health topics on Twitter. MATERIALS AND METHODS: We collected data on 176 million tweets from 2011 to 2014 with content related to depression or suicide. Using an autoregressive integrated moving average (ARIMA) data analysis, we identified deviations from predicted trends in communication about depression and suicide. RESULTS: Two types of heightened Twitter activity regarding depression or suicide were identified in 2014: expected increases in response to planned behavioral health events, and unexpected increases in response to unanticipated events. Tweet volume following expected increases went back to the predicted level more rapidly than the volume following unexpected events. DISCUSSION: Although ARIMA models have been used extensively in other fields, they have not been used widely in public health. Our findings indicate that our ARIMA model is valid for identifying periods of heightened activity on Twitter related to behavioral health. The model offers an objective and empirically based measure to identify periods of greater interest for timing the dissemination of credible information related to mental health. CONCLUSION: Spikes in tweet volume following a behavioral health event often last for less than 2 days. Individuals and organizations that want to disseminate behavioral health messages on Twitter in response to heightened periods of interest need to take this limited time frame into account. Published by Oxford University Press on behalf of the American Medical Informatics Association 2016. This work is written by US Government employees and is in the public domain in the United States.
Entities:
Keywords:
ARIMA; Twitter; health communication; mental health; social media
Authors: Liliana Laranjo; Amaël Arguel; Ana L Neves; Aideen M Gallagher; Ruth Kaplan; Nathan Mortimer; Guilherme A Mendes; Annie Y S Lau Journal: J Am Med Inform Assoc Date: 2014-07-08 Impact factor: 4.497
Authors: Jenine K Harris; Sarah Moreland-Russell; Rachel G Tabak; Lindsay R Ruhr; Ryan C Maier Journal: Am J Public Health Date: 2014-05-15 Impact factor: 9.308
Authors: Wen-ying Sylvia Chou; Yvonne M Hunt; Ellen Burke Beckjord; Richard P Moser; Bradford W Hesse Journal: J Med Internet Res Date: 2009-11-27 Impact factor: 5.428
Authors: Rosemary Thackeray; Scott H Burton; Christophe Giraud-Carrier; Stephen Rollins; Catherine R Draper Journal: BMC Cancer Date: 2013-10-29 Impact factor: 4.430
Authors: Jason I Chen; Ginnifer L Mastarone; Santisia A Ambrosino; Nicole Anzalone; Kathleen F Carlson; Steven K Dobscha; Alan R Teo Journal: Crisis Date: 2019-04-02
Authors: Jason B Colditz; Kar-Hai Chu; Sherry L Emery; Chandler R Larkin; A Everette James; Joel Welling; Brian A Primack Journal: Am J Public Health Date: 2018-06-21 Impact factor: 9.308
Authors: Steven A Sumner; Stacey Galik; Jennifer Mathieu; Megan Ward; Thomas Kiley; Brad Bartholow; Alison Dingwall; Peter Mork Journal: J Adolesc Health Date: 2019-02-26 Impact factor: 5.012
Authors: Xi Chen; Stephen X Zhang; Asghar Afshar Jahanshahi; Aldo Alvarez-Risco; Huiyang Dai; Jizhen Li; Verónica García Ibarra Journal: JMIR Public Health Surveill Date: 2020-07-21