Generalizing from social media data: a formal theory approach
Researchers increasingly draw on social media data to answer big questions about social patterns and dynamics. However, as with any data source, social media data present both opportunities and significant challenges. One major critique of social media data is that the data are not
generalizable outside of the platforms from which the data originate. Problems of generalizability stem from non-universal participation rates on various platforms, demographically biased samples, as well as limited access to data based on infrastructural constraints and/or user privacy practices.
We suggest that instead of empirical generalizability, social media data are theoretically generalizable in the formal theory tradition. Through a case example in which we use YouTube comments to test and extend a key tenet of identity theory, we show how social media data can
instantiate theoretical variables and thus generalize to theoretical propositions. Mediated through formal theory, social media data maintain the capacity to address broad social questions while upholding methodological integrity.
Keywords: Generalizability; big data; formal theory; research methods; social media
Document Type: Research Article
Affiliations: School of Sociology, The Australian National University, Canberra, Australia
Publication date: 16 April 2019
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites
- Access Key
- Free content
- Partial Free content
- New content
- Open access content
- Partial Open access content
- Subscribed content
- Partial Subscribed content
- Free trial content