Papers by Stephan Poppe
Active Learning for Corpus Refinement: Cost-Effective Preprocessing to Improve Validity of Applied Quantitative Text Analysis (2026.eacl-srw)
Copied to clipboard
| Challenge: | Quantitative text analysis relies on high-quality corpora, but keyword-based collection often retrieves irrelevant material, undermining validity. |
| Approach: | They propose to use a transformer-based classifier to iteratively refine corpora by excluding irrelevant documents. |
| Outcome: | The proposed method outperforms random sampling and weakly supervised sampling and outperformed random sampling. |