· 2014
Latent dirichlet allocation
- 291citations
- 2014year
Short summary
This paper identifies instability in Latent Dirichlet Allocation (LDA) topic modeling and proposes a new similarity metric and vocabulary reduction criterion to address its limitations for qualitative social science analysis.
AI-generated from the title and abstract; the full text is not read.
Key points
- LDA topic modeling exhibits instability in its inference process.
- A new metric for measuring similarity between topics is proposed.
- A criterion for vocabulary reduction is introduced to improve LDA.
- LDA has limitations for qualitative social science analysis.
AI-generated from the title and abstract; the full text is not read.
Abstract
Topic modeling, in particular the Latent Dirichlet Allocation (LDA) model, has recently emerged as an important tool for understanding large datasets, in particular, user-generated datasets in social studies of the Web. In this work, we investigate the instability of LDA inference, propose a new metric of similarity between topics and a criterion of vocabulary reduction. We show the limitations of the LDA approach for the purposes of qualitative analysis in social science and sketch some ways for improvement.
The authors' abstract, as published at the source., 2014 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: General Social Sciences
General Social SciencesSocial Sciences