Details
| Original language | English |
|---|---|
| Pages (from-to) | 760-776 |
| Number of pages | 17 |
| Journal | Social science computer review |
| Volume | 42 |
| Issue number | 3 |
| Early online date | 13 Nov 2023 |
| Publication status | Published - Jun 2024 |
Abstract
For qualitative data analysis (QDA), researchers assign codes to text segments to arrange the information into topics or concepts. These annotations facilitate information retrieval and the identification of emerging patterns in unstructured data. However, this metadata is typically not published or reused after the research. Subsequent studies with similar research questions require a new definition of codes and do not benefit from other analysts’ experience. Machine learning (ML) based classification seeded with such data remains a challenging task due to the ambiguity of code definitions and the inherent subjectivity of the exercise. Previous attempts to support QDA using ML rely on linear models and only examined individual datasets that were either smaller or coded specifically for this purpose. However, we show that modern approaches effectively capture at least part of the codes’ semantics and may generalize to multiple studies. We analyze the performance of multiple classifiers across three large real-world datasets. Furthermore, we propose an ML-based approach to identify semantic relations of codes in different studies to show thematic faceting, enhance retrieval of related content, or bootstrap the coding process. These are encouraging results that suggest how analysts might benefit from prior interpretation efforts, potentially yielding new insights into qualitative data.
Keywords
- computational social science, machine learning, qualitative coding, qualitative data
ASJC Scopus subject areas
- Social Sciences(all)
- Computer Science(all)
- Computer Science Applications
- Social Sciences(all)
- Library and Information Sciences
- Social Sciences(all)
- Law
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Social science computer review, Vol. 42, No. 3, 06.2024, p. 760-776.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Bridging Qualitative Data Silos
T2 - The Potential of Reusing Codings Through Machine Learning Based Cross-Study Code Linking
AU - Wildemann, Sergej
AU - Niederée, Claudia
AU - Elejalde, Erick
N1 - Publisher Copyright: © The Author(s) 2023.
PY - 2024/6
Y1 - 2024/6
N2 - For qualitative data analysis (QDA), researchers assign codes to text segments to arrange the information into topics or concepts. These annotations facilitate information retrieval and the identification of emerging patterns in unstructured data. However, this metadata is typically not published or reused after the research. Subsequent studies with similar research questions require a new definition of codes and do not benefit from other analysts’ experience. Machine learning (ML) based classification seeded with such data remains a challenging task due to the ambiguity of code definitions and the inherent subjectivity of the exercise. Previous attempts to support QDA using ML rely on linear models and only examined individual datasets that were either smaller or coded specifically for this purpose. However, we show that modern approaches effectively capture at least part of the codes’ semantics and may generalize to multiple studies. We analyze the performance of multiple classifiers across three large real-world datasets. Furthermore, we propose an ML-based approach to identify semantic relations of codes in different studies to show thematic faceting, enhance retrieval of related content, or bootstrap the coding process. These are encouraging results that suggest how analysts might benefit from prior interpretation efforts, potentially yielding new insights into qualitative data.
AB - For qualitative data analysis (QDA), researchers assign codes to text segments to arrange the information into topics or concepts. These annotations facilitate information retrieval and the identification of emerging patterns in unstructured data. However, this metadata is typically not published or reused after the research. Subsequent studies with similar research questions require a new definition of codes and do not benefit from other analysts’ experience. Machine learning (ML) based classification seeded with such data remains a challenging task due to the ambiguity of code definitions and the inherent subjectivity of the exercise. Previous attempts to support QDA using ML rely on linear models and only examined individual datasets that were either smaller or coded specifically for this purpose. However, we show that modern approaches effectively capture at least part of the codes’ semantics and may generalize to multiple studies. We analyze the performance of multiple classifiers across three large real-world datasets. Furthermore, we propose an ML-based approach to identify semantic relations of codes in different studies to show thematic faceting, enhance retrieval of related content, or bootstrap the coding process. These are encouraging results that suggest how analysts might benefit from prior interpretation efforts, potentially yielding new insights into qualitative data.
KW - computational social science
KW - machine learning
KW - qualitative coding
KW - qualitative data
UR - http://www.scopus.com/inward/record.url?scp=85176945575&partnerID=8YFLogxK
U2 - 10.1177/08944393231215459
DO - 10.1177/08944393231215459
M3 - Article
AN - SCOPUS:85176945575
VL - 42
SP - 760
EP - 776
JO - Social science computer review
JF - Social science computer review
SN - 0894-4393
IS - 3
ER -