Computational grounded theory revisited: From computer-led to computer-assisted text analysis

Hjalmar Bang Carlsen; Snorre Ralund

doi:10.1177/20539517221080146

Computational grounded theory revisited: From computer-led to computer-assisted text analysis

Hjalmar Bang Carlsen^*
, Snorre Ralund

^*Corresponding author af dette arbejde

Publikation: Bidrag til tidsskrift/Konferencebidrag i tidsskrift /Bidrag til avis › Tidsskriftartikel › Forskning › peer review

36 Citationer (Scopus)

Abstract

The size and variation in both meaning-making and populations that characterize much contemporary text data demand research processes that support both discovery, interpretation and measurement. We assess one dominant strategy within the social sciences that takes a computer-led approach to text analysis. The approach is coined computational grounded theory. This strategy, we argue, relies on a set of unwarranted assumptions, namely, that unsupervised models return natural clusters of meaning, that the researcher can understand text with limited immersion and that indirect validation is sufficient for ensuring unbiased and precise measurement. In response to this criticism, we develop a framework that is computer assisted. We argue that our reformulation of computational grounded theory better aligns with the principles within grounded theory, anthropological theory generation and ethnography.

Originalsprog	Engelsk
Tidsskrift	Big Data and Society
Vol/bind	9
Nummer	1
ISSN	2053-9517
DOI	https://doi.org/10.1177/20539517221080146
Status	Udgivet - jan. 2022
Udgivet eksternt	Ja

Adgang til dokumentet

10.1177/20539517221080146Licens: CC BY-NC-ND

Biblioteksadgang?

Tjek tilgængelighed hos det Kgl. Bibliotek

Andre filer og links

Link to publication in Scopus

Citationsformater

@article{fd9b8d4aa4b04b95a933a6bbb27206ce,

title = "Computational grounded theory revisited: From computer-led to computer-assisted text analysis",

abstract = "The size and variation in both meaning-making and populations that characterize much contemporary text data demand research processes that support both discovery, interpretation and measurement. We assess one dominant strategy within the social sciences that takes a computer-led approach to text analysis. The approach is coined computational grounded theory. This strategy, we argue, relies on a set of unwarranted assumptions, namely, that unsupervised models return natural clusters of meaning, that the researcher can understand text with limited immersion and that indirect validation is sufficient for ensuring unbiased and precise measurement. In response to this criticism, we develop a framework that is computer assisted. We argue that our reformulation of computational grounded theory better aligns with the principles within grounded theory, anthropological theory generation and ethnography.",

keywords = "Computational text analysis, digital social research, grounded theory, interpretation, mixed methods",

author = "Carlsen, \{Hjalmar Bang\} and Snorre Ralund",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2022.",

year = "2022",

month = jan,

doi = "10.1177/20539517221080146",

language = "English",

volume = "9",

journal = "Big Data and Society",

issn = "2053-9517",

publisher = "SAGE Publications Ltd",

number = "1",

}

TY - JOUR

T1 - Computational grounded theory revisited

T2 - From computer-led to computer-assisted text analysis

AU - Carlsen, Hjalmar Bang

AU - Ralund, Snorre

N1 - Publisher Copyright: © The Author(s) 2022.

PY - 2022/1

Y1 - 2022/1

N2 - The size and variation in both meaning-making and populations that characterize much contemporary text data demand research processes that support both discovery, interpretation and measurement. We assess one dominant strategy within the social sciences that takes a computer-led approach to text analysis. The approach is coined computational grounded theory. This strategy, we argue, relies on a set of unwarranted assumptions, namely, that unsupervised models return natural clusters of meaning, that the researcher can understand text with limited immersion and that indirect validation is sufficient for ensuring unbiased and precise measurement. In response to this criticism, we develop a framework that is computer assisted. We argue that our reformulation of computational grounded theory better aligns with the principles within grounded theory, anthropological theory generation and ethnography.

AB - The size and variation in both meaning-making and populations that characterize much contemporary text data demand research processes that support both discovery, interpretation and measurement. We assess one dominant strategy within the social sciences that takes a computer-led approach to text analysis. The approach is coined computational grounded theory. This strategy, we argue, relies on a set of unwarranted assumptions, namely, that unsupervised models return natural clusters of meaning, that the researcher can understand text with limited immersion and that indirect validation is sufficient for ensuring unbiased and precise measurement. In response to this criticism, we develop a framework that is computer assisted. We argue that our reformulation of computational grounded theory better aligns with the principles within grounded theory, anthropological theory generation and ethnography.

KW - Computational text analysis

KW - digital social research

KW - grounded theory

KW - interpretation

KW - mixed methods

UR - https://www.scopus.com/pages/publications/85126647555

U2 - 10.1177/20539517221080146

DO - 10.1177/20539517221080146

M3 - Journal article

AN - SCOPUS:85126647555

SN - 2053-9517

VL - 9

JO - Big Data and Society

JF - Big Data and Society

IS - 1

ER -

Computational grounded theory revisited: From computer-led to computer-assisted text analysis

Abstract

Adgang til dokumentet

Biblioteksadgang?

Andre filer og links

Fingeraftryk

Citationsformater