High-resolution temporal representations of alcohol and tobacco behaviors from social media data

Tom Huang, Anas Elghafari, Kunal Relia, Rumi Chunara

Research output: Contribution to journalArticle

Abstract

Understanding tobacco- and alcohol-related behavioral patterns is critical for uncovering risk factors and potentially designing targeted social computing intervention systems. Given that we make choices multiple times per day, hourly and daily patterns are critical for better understanding behaviors. Here, we combine natural language processing, machine learning and time series analyses to assess Twitter activity specifically related to alcohol and tobacco consumption and their sub-daily, daily and weekly cycles. Twitter self-reports of alcohol and tobacco use are compared to other data streams available at similar temporal resolution. We assess if discussion of drinking by inferred underage versus legal age people or discussion of use of different types of tobacco products can be differentiated using these temporal patterns. We find that time and frequency domain representations of behaviors on social media can provide meaningful and unique insights, and we discuss the types of behaviors for which the approach may be most useful.

Original languageEnglish (US)
Article number54
JournalProceedings of the ACM on Human-Computer Interaction
Volume1
Issue numberCSCW
DOIs
StatePublished - Nov 1 2017

Fingerprint

Tobacco
social media
nicotine
Alcohols
twitter
alcohol
legal age
tobacco consumption
social intervention
underage
alcohol consumption
time series
Learning systems
Time series
language
learning
Processing
time

Keywords

  • Alcohol
  • Behavior
  • Health
  • Natural language processing
  • Social media
  • Time-series
  • Tobacco

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Human-Computer Interaction
  • Social Sciences (miscellaneous)

Cite this

High-resolution temporal representations of alcohol and tobacco behaviors from social media data. / Huang, Tom; Elghafari, Anas; Relia, Kunal; Chunara, Rumi.

In: Proceedings of the ACM on Human-Computer Interaction, Vol. 1, No. CSCW, 54, 01.11.2017.

Research output: Contribution to journalArticle

@article{62e3e5e9f9a44c6eb34c053beb04e335,
title = "High-resolution temporal representations of alcohol and tobacco behaviors from social media data",
abstract = "Understanding tobacco- and alcohol-related behavioral patterns is critical for uncovering risk factors and potentially designing targeted social computing intervention systems. Given that we make choices multiple times per day, hourly and daily patterns are critical for better understanding behaviors. Here, we combine natural language processing, machine learning and time series analyses to assess Twitter activity specifically related to alcohol and tobacco consumption and their sub-daily, daily and weekly cycles. Twitter self-reports of alcohol and tobacco use are compared to other data streams available at similar temporal resolution. We assess if discussion of drinking by inferred underage versus legal age people or discussion of use of different types of tobacco products can be differentiated using these temporal patterns. We find that time and frequency domain representations of behaviors on social media can provide meaningful and unique insights, and we discuss the types of behaviors for which the approach may be most useful.",
keywords = "Alcohol, Behavior, Health, Natural language processing, Social media, Time-series, Tobacco",
author = "Tom Huang and Anas Elghafari and Kunal Relia and Rumi Chunara",
year = "2017",
month = "11",
day = "1",
doi = "10.1145/3134689",
language = "English (US)",
volume = "1",
journal = "Proceedings of the ACM on Human-Computer Interaction",
issn = "2573-0142",
publisher = "Association for Computing Machinery (ACM)",
number = "CSCW",

}

TY - JOUR

T1 - High-resolution temporal representations of alcohol and tobacco behaviors from social media data

AU - Huang, Tom

AU - Elghafari, Anas

AU - Relia, Kunal

AU - Chunara, Rumi

PY - 2017/11/1

Y1 - 2017/11/1

N2 - Understanding tobacco- and alcohol-related behavioral patterns is critical for uncovering risk factors and potentially designing targeted social computing intervention systems. Given that we make choices multiple times per day, hourly and daily patterns are critical for better understanding behaviors. Here, we combine natural language processing, machine learning and time series analyses to assess Twitter activity specifically related to alcohol and tobacco consumption and their sub-daily, daily and weekly cycles. Twitter self-reports of alcohol and tobacco use are compared to other data streams available at similar temporal resolution. We assess if discussion of drinking by inferred underage versus legal age people or discussion of use of different types of tobacco products can be differentiated using these temporal patterns. We find that time and frequency domain representations of behaviors on social media can provide meaningful and unique insights, and we discuss the types of behaviors for which the approach may be most useful.

AB - Understanding tobacco- and alcohol-related behavioral patterns is critical for uncovering risk factors and potentially designing targeted social computing intervention systems. Given that we make choices multiple times per day, hourly and daily patterns are critical for better understanding behaviors. Here, we combine natural language processing, machine learning and time series analyses to assess Twitter activity specifically related to alcohol and tobacco consumption and their sub-daily, daily and weekly cycles. Twitter self-reports of alcohol and tobacco use are compared to other data streams available at similar temporal resolution. We assess if discussion of drinking by inferred underage versus legal age people or discussion of use of different types of tobacco products can be differentiated using these temporal patterns. We find that time and frequency domain representations of behaviors on social media can provide meaningful and unique insights, and we discuss the types of behaviors for which the approach may be most useful.

KW - Alcohol

KW - Behavior

KW - Health

KW - Natural language processing

KW - Social media

KW - Time-series

KW - Tobacco

UR - http://www.scopus.com/inward/record.url?scp=85055944238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055944238&partnerID=8YFLogxK

U2 - 10.1145/3134689

DO - 10.1145/3134689

M3 - Article

VL - 1

JO - Proceedings of the ACM on Human-Computer Interaction

JF - Proceedings of the ACM on Human-Computer Interaction

SN - 2573-0142

IS - CSCW

M1 - 54

ER -