Large-scale automated analysis of news media: A novel computational method for obesity policy research

Rita Hamad, Jennifer L. Pomeranz, Arjumand Siddiqi, Sanjay Basu

Research output: Contribution to journalArticle

Abstract

Objective Analyzing news media allows obesity policy researchers to understand popular conceptions about obesity, which is important for targeting health education and policies. A persistent dilemma is that investigators have to read and manually classify thousands of individual news articles to identify how obesity and obesity-related policy proposals may be described to the public in the media. A machine learning method called "automated content analysis" that permits researchers to train computers to "read" and classify massive volumes of documents was demonstrated. Methods 14,302 newspaper articles that mentioned the word "obesity" during 2011-2012 were identified. Four states that vary in obesity prevalence and policy (Alabama, California, New Jersey, and North Carolina) were examined. The reliability of an automated program to categorize the media's framing of obesity as an individual-level problem (e.g., diet) and/or an environmental-level problem (e.g., obesogenic environment) was tested. Results The automated program performed similarly to human coders. The proportion of articles with individual-level framing (27.7-31.0%) was higher than the proportion with neutral (18.0-22.1%) or environmental-level framing (16.0-16.4%) across all states and over the entire study period (P-

Original languageEnglish (US)
Pages (from-to)296-300
Number of pages5
JournalObesity
Volume23
Issue number2
DOIs
StatePublished - Feb 1 2015

Fingerprint

Obesity
Research
Research Personnel
Newspapers
Health Policy
Health Education
Diet

ASJC Scopus subject areas

  • Endocrinology
  • Medicine (miscellaneous)
  • Endocrinology, Diabetes and Metabolism
  • Nutrition and Dietetics

Cite this

Large-scale automated analysis of news media : A novel computational method for obesity policy research. / Hamad, Rita; Pomeranz, Jennifer L.; Siddiqi, Arjumand; Basu, Sanjay.

In: Obesity, Vol. 23, No. 2, 01.02.2015, p. 296-300.

Research output: Contribution to journalArticle

Hamad, Rita ; Pomeranz, Jennifer L. ; Siddiqi, Arjumand ; Basu, Sanjay. / Large-scale automated analysis of news media : A novel computational method for obesity policy research. In: Obesity. 2015 ; Vol. 23, No. 2. pp. 296-300.
@article{4b263b354bd849d0b49caee8fb99236a,
title = "Large-scale automated analysis of news media: A novel computational method for obesity policy research",
abstract = "Objective Analyzing news media allows obesity policy researchers to understand popular conceptions about obesity, which is important for targeting health education and policies. A persistent dilemma is that investigators have to read and manually classify thousands of individual news articles to identify how obesity and obesity-related policy proposals may be described to the public in the media. A machine learning method called {"}automated content analysis{"} that permits researchers to train computers to {"}read{"} and classify massive volumes of documents was demonstrated. Methods 14,302 newspaper articles that mentioned the word {"}obesity{"} during 2011-2012 were identified. Four states that vary in obesity prevalence and policy (Alabama, California, New Jersey, and North Carolina) were examined. The reliability of an automated program to categorize the media's framing of obesity as an individual-level problem (e.g., diet) and/or an environmental-level problem (e.g., obesogenic environment) was tested. Results The automated program performed similarly to human coders. The proportion of articles with individual-level framing (27.7-31.0{\%}) was higher than the proportion with neutral (18.0-22.1{\%}) or environmental-level framing (16.0-16.4{\%}) across all states and over the entire study period (P-",
author = "Rita Hamad and Pomeranz, {Jennifer L.} and Arjumand Siddiqi and Sanjay Basu",
year = "2015",
month = "2",
day = "1",
doi = "10.1002/oby.20955",
language = "English (US)",
volume = "23",
pages = "296--300",
journal = "Obesity",
issn = "1930-7381",
publisher = "Wiley-Blackwell",
number = "2",

}

TY - JOUR

T1 - Large-scale automated analysis of news media

T2 - A novel computational method for obesity policy research

AU - Hamad, Rita

AU - Pomeranz, Jennifer L.

AU - Siddiqi, Arjumand

AU - Basu, Sanjay

PY - 2015/2/1

Y1 - 2015/2/1

N2 - Objective Analyzing news media allows obesity policy researchers to understand popular conceptions about obesity, which is important for targeting health education and policies. A persistent dilemma is that investigators have to read and manually classify thousands of individual news articles to identify how obesity and obesity-related policy proposals may be described to the public in the media. A machine learning method called "automated content analysis" that permits researchers to train computers to "read" and classify massive volumes of documents was demonstrated. Methods 14,302 newspaper articles that mentioned the word "obesity" during 2011-2012 were identified. Four states that vary in obesity prevalence and policy (Alabama, California, New Jersey, and North Carolina) were examined. The reliability of an automated program to categorize the media's framing of obesity as an individual-level problem (e.g., diet) and/or an environmental-level problem (e.g., obesogenic environment) was tested. Results The automated program performed similarly to human coders. The proportion of articles with individual-level framing (27.7-31.0%) was higher than the proportion with neutral (18.0-22.1%) or environmental-level framing (16.0-16.4%) across all states and over the entire study period (P-

AB - Objective Analyzing news media allows obesity policy researchers to understand popular conceptions about obesity, which is important for targeting health education and policies. A persistent dilemma is that investigators have to read and manually classify thousands of individual news articles to identify how obesity and obesity-related policy proposals may be described to the public in the media. A machine learning method called "automated content analysis" that permits researchers to train computers to "read" and classify massive volumes of documents was demonstrated. Methods 14,302 newspaper articles that mentioned the word "obesity" during 2011-2012 were identified. Four states that vary in obesity prevalence and policy (Alabama, California, New Jersey, and North Carolina) were examined. The reliability of an automated program to categorize the media's framing of obesity as an individual-level problem (e.g., diet) and/or an environmental-level problem (e.g., obesogenic environment) was tested. Results The automated program performed similarly to human coders. The proportion of articles with individual-level framing (27.7-31.0%) was higher than the proportion with neutral (18.0-22.1%) or environmental-level framing (16.0-16.4%) across all states and over the entire study period (P-

UR - http://www.scopus.com/inward/record.url?scp=84922735936&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922735936&partnerID=8YFLogxK

U2 - 10.1002/oby.20955

DO - 10.1002/oby.20955

M3 - Article

C2 - 25522013

AN - SCOPUS:84922735936

VL - 23

SP - 296

EP - 300

JO - Obesity

JF - Obesity

SN - 1930-7381

IS - 2

ER -