liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Computational Text Analysis for Building and Testing Social Theory
Linköping University, Department of Management and Engineering, The Institute for Analytical Sociology, IAS. Linköping University, Faculty of Arts and Sciences.ORCID iD: 0000-0002-8467-1746
Linköping University, Department of Management and Engineering, The Institute for Analytical Sociology, IAS. Linköping University, Faculty of Arts and Sciences. Linköping University, The Institute for Analytical Sociology, IAS. Univ Leipzig, Germany.ORCID iD: 0000-0001-5774-1553
Univ Utrecht, Netherlands.
Linköping University, Department of Management and Engineering, The Institute for Analytical Sociology, IAS. Linköping University, Faculty of Arts and Sciences. Uppsala Univ, Sweden.
2026 (English)In: Kölner Zeitschrift für Soziologie und Sozialpsychologie, ISSN 0023-2653, E-ISSN 1861-891X, Vol. 78, no 3, p. 1059-1088Article in journal (Refereed) Published
Abstract [en]

Digitization and advances in natural language processing have transformed how sociologists can measure, model, and interpret social life through text. We provide an overview of computational text analysis as a methodological tool kit for building and testing social theory. The field is moving from descriptive uses toward theory-driven and causal inference approaches, though methodological standards-especially around data quality, reproducibility, and causal claims-remain inconsistent. Organizing approaches into data-first, theory-first, and theory-data integration paradigms, we highlight how different methods each balance inductive discovery with theoretical specification. We conceptualize text-analytic methods as measurement strategies that extract sociologically relevant information from unstructured language data and show how they can be incorporated into both thick descriptions and causal inference workflows. Taken together, various computational text analysis approaches offer researchers new opportunities to recover latent constructs, bridge quantitative scale with qualitative depth, and revitalize interpretive approaches in sociology. Digitalisierung und Fortschritte in der automatisierten Sprachverarbeitung ver & auml;nderten die M & ouml;glichkeiten der Soziologie zur Vermessung, Modellierung und Interpretation des sozialen Lebens durch Text. Dieser Beitrag gibt einen & Uuml;berblick & uuml;ber die computergest & uuml;tzte Textanalyse als methodischen Werkzeugkasten zur Entwicklung und Pr & uuml;fung sozialwissenschaftlicher Theorien. Das Feld entwickelt sich von Beschreibungen hin zu theoriegeleiteten und kausalanalytischen Anwendungen; zugleich bleiben methodische Standards, insbesondere hinsichtlich Datenqualit & auml;t, Reproduzierbarkeit und kausaler Inferenz, noch immer uneinheitlich. Wir ordnen bestehende Ans & auml;tze in datengetriebene, theoriegeleitete und integrierende Paradigmen ein und arbeiten heraus, wie unterschiedliche Methoden das Spannungsverh & auml;ltnis zwischen induktiver Exploration und theoretischer Spezifikation ausbalancieren. Textanalytische Verfahren verstehen wir als Messstrategien zur Erschlie ss ung soziologisch relevanter Informationen aus unstrukturierten Textdaten und verdeutlichen, wie sich diese Verfahren sowohl f & uuml;r dichte Beschreibungen als auch f & uuml;r kausalanalytische Forschungsdesigns nutzen lassen. Insgesamt er & ouml;ffnet die computergest & uuml;tzte Textanalyse neue M & ouml;glichkeiten, latente Konstrukte zu erfassen, quantitative Reichweite mit qualitativer Tiefensch & auml;rfe zu verbinden und interpretative Ans & auml;tze in der Soziologie neu zu beleben.

Place, publisher, year, edition, pages
SPRINGER VIEWEG-SPRINGER FACHMEDIEN WIESBADEN GMBH , 2026. Vol. 78, no 3, p. 1059-1088
Keywords [en]
Natural language processing; Large language models; Text as data; Description; Causal inference; Automatisierte Sprachverarbeitung; Text als Daten; Deskription; Kausale Inferenz
National Category
Natural Language Processing
Identifiers
URN: urn:nbn:se:liu:diva-222367DOI: 10.1007/s11577-026-01065-wISI: 001717328600001Scopus ID: 2-s2.0-105034105861OAI: oai:DiVA.org:liu-222367DiVA, id: diva2:2049807
Note

Funding Agencies|Linkping University

Available from: 2026-03-31 Created: 2026-03-31 Last updated: 2026-09-22Bibliographically approved

Open Access in DiVA

fulltext(495 kB)10 downloads
File information
File name FULLTEXT01.pdfFile size 495 kBChecksum SHA-512
6fdbcca82d36fec648e99ce420e8e31b1c26b1035921229df316d3907dd7eaf5925d21bbbed2533d0f300c086b165446ecdb26744fac1c14e4aeacabdd0e93f9
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Hurtado Bodell, MiriamKeuschnigg, MarcMenshikova, Anastasia

Search in DiVA

By author/editor
Hurtado Bodell, MiriamKeuschnigg, MarcMenshikova, Anastasia
By organisation
The Institute for Analytical Sociology, IASFaculty of Arts and SciencesThe Institute for Analytical Sociology, IAS
In the same journal
Kölner Zeitschrift für Soziologie und Sozialpsychologie
Natural Language Processing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 71 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf