Analyzing social media data: A mixed-methods framework combining computational and qualitative text analysis

Matthew Andreotta, Robertus Nugroho, Mark Hurlstone, Fabio Boschetti, Simon Farrell, Iain WALKER, Cécile Paris

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

To qualitative researchers, social media offers a novel opportunity to harvest a massive and diverse range of content without the need for intrusive or intensive data collection procedures. However, performing a qualitative analysis across a massive social media data set is cumbersome and impractical. Instead, researchers often extract a subset of content to analyze, but a framework to facilitate this process is currently lacking. We present a four-phased framework for improving this extraction process, which blends the capacities of data science techniques to compress large data sets into smaller spaces, with the capabilities of qualitative analysis to address research questions. We demonstrate this framework by investigating the topics of Australian Twitter commentary on climate change, using quantitative (non-negative matrix inter-joint factorization; topic alignment) and qualitative (thematic analysis) techniques. Our approach is useful for researchers seeking to perform qualitative analyses of social media, or researchers wanting to supplement their quantitative work with a qualitative analysis of broader social context and meaning.
Original languageEnglish
Pages (from-to)1766-1781
Number of pages16
JournalBehavior Research Methods
Volume51
Issue number4
Early online date2019
DOIs
Publication statusPublished - 15 Aug 2019

Fingerprint

Social Media
Research Personnel
Climate Change
Joints
Computational
Mixed Methods
Text Analysis
Research
Qualitative Analysis
Datasets

Cite this

Andreotta, Matthew ; Nugroho, Robertus ; Hurlstone, Mark ; Boschetti, Fabio ; Farrell, Simon ; WALKER, Iain ; Paris, Cécile. / Analyzing social media data: A mixed-methods framework combining computational and qualitative text analysis. In: Behavior Research Methods. 2019 ; Vol. 51, No. 4. pp. 1766-1781.
@article{a98e6534f822443a9822d9d4580e3f4c,
title = "Analyzing social media data: A mixed-methods framework combining computational and qualitative text analysis",
abstract = "To qualitative researchers, social media offers a novel opportunity to harvest a massive and diverse range of content without the need for intrusive or intensive data collection procedures. However, performing a qualitative analysis across a massive social media data set is cumbersome and impractical. Instead, researchers often extract a subset of content to analyze, but a framework to facilitate this process is currently lacking. We present a four-phased framework for improving this extraction process, which blends the capacities of data science techniques to compress large data sets into smaller spaces, with the capabilities of qualitative analysis to address research questions. We demonstrate this framework by investigating the topics of Australian Twitter commentary on climate change, using quantitative (non-negative matrix inter-joint factorization; topic alignment) and qualitative (thematic analysis) techniques. Our approach is useful for researchers seeking to perform qualitative analyses of social media, or researchers wanting to supplement their quantitative work with a qualitative analysis of broader social context and meaning.",
keywords = "Big data, Climate change, Joint matrix factorization, Thematic analysis, Topic alignment, Topic modeling, Twitter",
author = "Matthew Andreotta and Robertus Nugroho and Mark Hurlstone and Fabio Boschetti and Simon Farrell and Iain WALKER and C{\'e}cile Paris",
year = "2019",
month = "8",
day = "15",
doi = "10.3758/s13428-019-01202-8",
language = "English",
volume = "51",
pages = "1766--1781",
journal = "Behavior Research Methods, Instruments, and Computers",
issn = "1554-351X",
publisher = "Springer",
number = "4",

}

Analyzing social media data: A mixed-methods framework combining computational and qualitative text analysis. / Andreotta, Matthew; Nugroho, Robertus; Hurlstone, Mark; Boschetti, Fabio; Farrell, Simon; WALKER, Iain; Paris, Cécile.

In: Behavior Research Methods, Vol. 51, No. 4, 15.08.2019, p. 1766-1781.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Analyzing social media data: A mixed-methods framework combining computational and qualitative text analysis

AU - Andreotta, Matthew

AU - Nugroho, Robertus

AU - Hurlstone, Mark

AU - Boschetti, Fabio

AU - Farrell, Simon

AU - WALKER, Iain

AU - Paris, Cécile

PY - 2019/8/15

Y1 - 2019/8/15

N2 - To qualitative researchers, social media offers a novel opportunity to harvest a massive and diverse range of content without the need for intrusive or intensive data collection procedures. However, performing a qualitative analysis across a massive social media data set is cumbersome and impractical. Instead, researchers often extract a subset of content to analyze, but a framework to facilitate this process is currently lacking. We present a four-phased framework for improving this extraction process, which blends the capacities of data science techniques to compress large data sets into smaller spaces, with the capabilities of qualitative analysis to address research questions. We demonstrate this framework by investigating the topics of Australian Twitter commentary on climate change, using quantitative (non-negative matrix inter-joint factorization; topic alignment) and qualitative (thematic analysis) techniques. Our approach is useful for researchers seeking to perform qualitative analyses of social media, or researchers wanting to supplement their quantitative work with a qualitative analysis of broader social context and meaning.

AB - To qualitative researchers, social media offers a novel opportunity to harvest a massive and diverse range of content without the need for intrusive or intensive data collection procedures. However, performing a qualitative analysis across a massive social media data set is cumbersome and impractical. Instead, researchers often extract a subset of content to analyze, but a framework to facilitate this process is currently lacking. We present a four-phased framework for improving this extraction process, which blends the capacities of data science techniques to compress large data sets into smaller spaces, with the capabilities of qualitative analysis to address research questions. We demonstrate this framework by investigating the topics of Australian Twitter commentary on climate change, using quantitative (non-negative matrix inter-joint factorization; topic alignment) and qualitative (thematic analysis) techniques. Our approach is useful for researchers seeking to perform qualitative analyses of social media, or researchers wanting to supplement their quantitative work with a qualitative analysis of broader social context and meaning.

KW - Big data

KW - Climate change

KW - Joint matrix factorization

KW - Thematic analysis

KW - Topic alignment

KW - Topic modeling

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85064345090&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/analyzing-social-media-data-mixedmethods-framework-combining-computational-qualitative-text-analysis

U2 - 10.3758/s13428-019-01202-8

DO - 10.3758/s13428-019-01202-8

M3 - Article

VL - 51

SP - 1766

EP - 1781

JO - Behavior Research Methods, Instruments, and Computers

JF - Behavior Research Methods, Instruments, and Computers

SN - 1554-351X

IS - 4

ER -