What We Can Do and Cannot Do with Topic Modeling: A Systematic Review

Chen, Yingying; Peng, Zhao; Kim, Sei‐Hill; Choi, Changwon

doi:10.1080/19312458.2023.2167965

Cited by 11 publications

(1 citation statement)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Topic modelling offers an alternative to qualitative coding for textual analysis of large text collections. According to Chen et al (2023), topic modelling can be applied to (i) gain a quick overview of the major contents from large unstructured, text collections by transforming a large sample of text into a much smaller set of topics; (ii) provide a new lens for scholars to identify patterns that would otherwise be undetectable with manual coding alone from a massive number of texts; and (iii) extract certain meanings from the text data. Moreover, the generated topics lack context, therefore the qualitative analysis provides the means to manual screening, interpretation and labelling each topic by inspecting the words and the documents they are contained in.…”

Section: Mixed Methods Approachmentioning

confidence: 99%

COVID-19 Vaccine Hesitancy

Hammarlin,

Kokkinakis,

Borin

2023

jdsr

View full text Add to dashboard Cite

In this article, hesitancy towards COVID-19 vaccinations is investigated as a phenomenon touching upon existential questions. We argue that it encompasses ideas of illness and health, and also of dying and fear of suffering. Building on a specific strand within anti-vaccination studies, we conjecture that vaccine hesitancy is, to some extent, reasonable, and that this scepticism should be studied with compassion. Through a mixed methods approach, vaccine hesitancy, as it is being expressed in a Swedish digital open forum, is investigated and understood as, on the one hand, a perceived need of protecting one’s body from techno-scientific experiments, and thus the risk of becoming a victim of medicine itself. On the other hand, the community members express what we call a tacit belief in modern medicine by demonstrating their own “expert” pandemic knowledge. The analysis also shows how the COVID-19 pandemic triggers memories of another pandemic, namely the swine flu in 2009–2010, and what we term a medical crisis that occurred then, due to a vaccine that caused a rare but severe side effect in Sweden and elsewhere.

show abstract

Section: Mixed Methods Approachmentioning

confidence: 99%

COVID-19 Vaccine Hesitancy

Hammarlin,

Kokkinakis,

Borin

2023

jdsr

View full text Add to dashboard Cite

show abstract

The interactive Leipzig Corpus Miner: An extensible and adaptable text analysis tool for content analysis

Niekler,

Kahmann,

Burghardt

et al. 2023

Publizistik

View full text Add to dashboard Cite

We present the interactive Leipzig Corpus Miner (iLCM), which is the result of the development of an integrated research environment for the analysis of text data. The key features of iLCM compared to existing software tools for computer-assisted text analysis are its flexibility and scalability. The tool includes functions to offer commonly needed methods for automatic processing of text, such as preprocessing, standard text analysis, and visualization, which would be very time consuming without a ready-to-use software tool. To also provide more methodological flexibility, the iLCM is not tied to one specific class of research question, but can easily be extended to other applications. In this article, we will focus on the capabilities and the aspects of adaptability, extensibility, and data exchange with other tools from the field of empirical content analysis. We will present the features of the iLCM and showcase individual examples and a case study that demonstrates the practical use of the tool.

show abstract