Assessing behavioral stages from social media data

Jason Liu, Elissa R. Weitzman, Rumi Chunara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Important work rooted in psychological theory posits that health behavior change occurs through a series of discrete stages. Our work builds on the field of social computing by identifying how social media data can be used to resolve behavior stages at high resolution (e.g. hourly/daily) for key population subgroups and times. In essence this approach opens new opportunities to advance psychological theories and better understand how our health is shaped based on the real, dynamic, and rapid actions we make every day. To do so, we bring together domain knowledge and machine learning methods to form a hierarchical classification of Twitter data that resolves different stages of behavior. We identify and examine temporal patterns of the identified stages, with alcohol as a use case (planning or looking to drink, currently drinking, and reflecting on drinking). Known seasonal trends are compared with findings from our methods. We discuss the potential health policy implications of detecting high frequency behavior stages.

Original languageEnglish (US)
Title of host publicationCSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing
PublisherAssociation for Computing Machinery
Pages1320-1333
Number of pages14
ISBN (Electronic)9781450343350
DOIs
StatePublished - Feb 25 2017
Event2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, CSCW 2017 - Portland, United States
Duration: Feb 25 2017Mar 1 2017

Other

Other2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, CSCW 2017
CountryUnited States
CityPortland
Period2/25/173/1/17

Fingerprint

Health
Learning systems
Alcohols
Planning

Keywords

  • Behavior
  • Health
  • Hierarchical classification
  • Natural language processing
  • Social media

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications
  • Human-Computer Interaction

Cite this

Liu, J., Weitzman, E. R., & Chunara, R. (2017). Assessing behavioral stages from social media data. In CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing (pp. 1320-1333). Association for Computing Machinery. https://doi.org/10.1145/2998181.2998336

Assessing behavioral stages from social media data. / Liu, Jason; Weitzman, Elissa R.; Chunara, Rumi.

CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery, 2017. p. 1320-1333.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, J, Weitzman, ER & Chunara, R 2017, Assessing behavioral stages from social media data. in CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery, pp. 1320-1333, 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, CSCW 2017, Portland, United States, 2/25/17. https://doi.org/10.1145/2998181.2998336
Liu J, Weitzman ER, Chunara R. Assessing behavioral stages from social media data. In CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery. 2017. p. 1320-1333 https://doi.org/10.1145/2998181.2998336
Liu, Jason ; Weitzman, Elissa R. ; Chunara, Rumi. / Assessing behavioral stages from social media data. CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. Association for Computing Machinery, 2017. pp. 1320-1333
@inproceedings{ac52422c31b642b79ee9f4e0bae7feee,
title = "Assessing behavioral stages from social media data",
abstract = "Important work rooted in psychological theory posits that health behavior change occurs through a series of discrete stages. Our work builds on the field of social computing by identifying how social media data can be used to resolve behavior stages at high resolution (e.g. hourly/daily) for key population subgroups and times. In essence this approach opens new opportunities to advance psychological theories and better understand how our health is shaped based on the real, dynamic, and rapid actions we make every day. To do so, we bring together domain knowledge and machine learning methods to form a hierarchical classification of Twitter data that resolves different stages of behavior. We identify and examine temporal patterns of the identified stages, with alcohol as a use case (planning or looking to drink, currently drinking, and reflecting on drinking). Known seasonal trends are compared with findings from our methods. We discuss the potential health policy implications of detecting high frequency behavior stages.",
keywords = "Behavior, Health, Hierarchical classification, Natural language processing, Social media",
author = "Jason Liu and Weitzman, {Elissa R.} and Rumi Chunara",
year = "2017",
month = "2",
day = "25",
doi = "10.1145/2998181.2998336",
language = "English (US)",
pages = "1320--1333",
booktitle = "CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Assessing behavioral stages from social media data

AU - Liu, Jason

AU - Weitzman, Elissa R.

AU - Chunara, Rumi

PY - 2017/2/25

Y1 - 2017/2/25

N2 - Important work rooted in psychological theory posits that health behavior change occurs through a series of discrete stages. Our work builds on the field of social computing by identifying how social media data can be used to resolve behavior stages at high resolution (e.g. hourly/daily) for key population subgroups and times. In essence this approach opens new opportunities to advance psychological theories and better understand how our health is shaped based on the real, dynamic, and rapid actions we make every day. To do so, we bring together domain knowledge and machine learning methods to form a hierarchical classification of Twitter data that resolves different stages of behavior. We identify and examine temporal patterns of the identified stages, with alcohol as a use case (planning or looking to drink, currently drinking, and reflecting on drinking). Known seasonal trends are compared with findings from our methods. We discuss the potential health policy implications of detecting high frequency behavior stages.

AB - Important work rooted in psychological theory posits that health behavior change occurs through a series of discrete stages. Our work builds on the field of social computing by identifying how social media data can be used to resolve behavior stages at high resolution (e.g. hourly/daily) for key population subgroups and times. In essence this approach opens new opportunities to advance psychological theories and better understand how our health is shaped based on the real, dynamic, and rapid actions we make every day. To do so, we bring together domain knowledge and machine learning methods to form a hierarchical classification of Twitter data that resolves different stages of behavior. We identify and examine temporal patterns of the identified stages, with alcohol as a use case (planning or looking to drink, currently drinking, and reflecting on drinking). Known seasonal trends are compared with findings from our methods. We discuss the potential health policy implications of detecting high frequency behavior stages.

KW - Behavior

KW - Health

KW - Hierarchical classification

KW - Natural language processing

KW - Social media

UR - http://www.scopus.com/inward/record.url?scp=85014802012&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014802012&partnerID=8YFLogxK

U2 - 10.1145/2998181.2998336

DO - 10.1145/2998181.2998336

M3 - Conference contribution

AN - SCOPUS:85014802012

SP - 1320

EP - 1333

BT - CSCW 2017 - Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing

PB - Association for Computing Machinery

ER -