Schulze, Patrick and Wiegrebe, Simon and Thurner, Paul W. and Heumann, Christian and Assenmacher, Matthias (2023) A Bayesian approach to modeling topic-metadata relationships. ASTA-ADVANCES IN STATISTICAL ANALYSIS. ISSN 1863-8171, 1863-818X
Full text not available from this repository. (Request a copy)Abstract
The objective of advanced topic modeling is not only to explore latent topical structures, but also to estimate relationships between the discovered topics and theoretically relevant metadata. Methods used to estimate such relationships must take into account that the topical structure is not directly observed, but instead being estimated itself in an unsupervised fashion, usually by common topic models. A frequently used procedure to achieve this is the method of composition, a Monte Carlo sampling technique performing multiple repeated linear regressions of sampled topic proportions on metadata covariates. In this paper, we propose two modifications of this approach: First, we substantially refine the existing implementation of the method of composition from the R package stm by replacing linear regression with the more appropriate Beta regression. Second, we provide a fundamental enhancement of the entire estimation framework by substituting the current blending of frequentist and Bayesian methods with a fully Bayesian approach. This allows for a more appropriate quantification of uncertainty. We illustrate our improved methodology by investigating relationships between Twitter posts by German parliamentarians and different metadata covariates related to their electoral districts, using the structural topic model to estimate topic proportions.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | TEXT; Natural language processing; Topic modeling; Topic-metadata relationships; Bayesian statistics; Beta regression; Twitter data |
| Subjects: | 600 Technology > 610 Medical sciences Medicine |
| Divisions: | Medicine > Institut für Epidemiologie und Präventivmedizin > Lehrstuhl für Genetische Epidemiologie |
| Depositing User: | Dr. Gernot Deinzer |
| Date Deposited: | 13 Mar 2024 09:59 |
| Last Modified: | 13 Mar 2024 09:59 |
| URI: | https://pred.uni-regensburg.de/id/eprint/59530 |
Actions (login required)
 |
View Item |
