Content Analysis in an Era of Big Data: A Hybrid Approach to Computational and Manual Methods

Seth C. Lewis, Rodrigo Zamith, Alfred Hermida

Research output: Contribution to journalArticle

140 Citations (Scopus)

Abstract

Massive datasets of communication are challenging traditional, human-driven approaches to content analysis. Computational methods present enticing solutions to these problems but in many cases are insufficient on their own. We argue that an approach blending computational and manual methods throughout the content analysis process may yield more fruitful results, and draw on a case study of news sourcing on Twitter to illustrate this hybrid approach in action. Careful combinations of computational and manual techniques can preserve the strengths of traditional content analysis, with its systematic rigor and contextual sensitivity, while also maximizing the large-scale capacity of Big Data and the algorithmic accuracy of computational methods.

Original languageEnglish (US)
Pages (from-to)34-52
Number of pages19
JournalJournal of Broadcasting and Electronic Media
Volume57
Issue number1
DOIs
StatePublished - Jan 2013

Fingerprint

Computational methods
content analysis
twitter
Communication
news
communication
present
Big data

Cite this

Content Analysis in an Era of Big Data : A Hybrid Approach to Computational and Manual Methods. / Lewis, Seth C.; Zamith, Rodrigo; Hermida, Alfred.

In: Journal of Broadcasting and Electronic Media, Vol. 57, No. 1, 01.2013, p. 34-52.

Research output: Contribution to journalArticle

Lewis, Seth C. ; Zamith, Rodrigo ; Hermida, Alfred. / Content Analysis in an Era of Big Data : A Hybrid Approach to Computational and Manual Methods. In: Journal of Broadcasting and Electronic Media. 2013 ; Vol. 57, No. 1. pp. 34-52.
@article{37e056cd66954dc181e2fdc5d1040db7,
title = "Content Analysis in an Era of Big Data: A Hybrid Approach to Computational and Manual Methods",
abstract = "Massive datasets of communication are challenging traditional, human-driven approaches to content analysis. Computational methods present enticing solutions to these problems but in many cases are insufficient on their own. We argue that an approach blending computational and manual methods throughout the content analysis process may yield more fruitful results, and draw on a case study of news sourcing on Twitter to illustrate this hybrid approach in action. Careful combinations of computational and manual techniques can preserve the strengths of traditional content analysis, with its systematic rigor and contextual sensitivity, while also maximizing the large-scale capacity of Big Data and the algorithmic accuracy of computational methods.",
author = "Lewis, {Seth C.} and Rodrigo Zamith and Alfred Hermida",
year = "2013",
month = "1",
doi = "10.1080/08838151.2012.761702",
language = "English (US)",
volume = "57",
pages = "34--52",
journal = "Journal of Broadcasting and Electronic Media",
issn = "0883-8151",
publisher = "Routledge",
number = "1",

}

TY - JOUR

T1 - Content Analysis in an Era of Big Data

T2 - A Hybrid Approach to Computational and Manual Methods

AU - Lewis, Seth C.

AU - Zamith, Rodrigo

AU - Hermida, Alfred

PY - 2013/1

Y1 - 2013/1

N2 - Massive datasets of communication are challenging traditional, human-driven approaches to content analysis. Computational methods present enticing solutions to these problems but in many cases are insufficient on their own. We argue that an approach blending computational and manual methods throughout the content analysis process may yield more fruitful results, and draw on a case study of news sourcing on Twitter to illustrate this hybrid approach in action. Careful combinations of computational and manual techniques can preserve the strengths of traditional content analysis, with its systematic rigor and contextual sensitivity, while also maximizing the large-scale capacity of Big Data and the algorithmic accuracy of computational methods.

AB - Massive datasets of communication are challenging traditional, human-driven approaches to content analysis. Computational methods present enticing solutions to these problems but in many cases are insufficient on their own. We argue that an approach blending computational and manual methods throughout the content analysis process may yield more fruitful results, and draw on a case study of news sourcing on Twitter to illustrate this hybrid approach in action. Careful combinations of computational and manual techniques can preserve the strengths of traditional content analysis, with its systematic rigor and contextual sensitivity, while also maximizing the large-scale capacity of Big Data and the algorithmic accuracy of computational methods.

UR - http://www.scopus.com/inward/record.url?scp=84875196985&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875196985&partnerID=8YFLogxK

U2 - 10.1080/08838151.2012.761702

DO - 10.1080/08838151.2012.761702

M3 - Article

AN - SCOPUS:84875196985

VL - 57

SP - 34

EP - 52

JO - Journal of Broadcasting and Electronic Media

JF - Journal of Broadcasting and Electronic Media

SN - 0883-8151

IS - 1

ER -