---
title: "Retrieving Floods without Floodlights: Topic Models as Binary"
description: "Media studies of extreme climate events often build corpora by searching news archives with hazard… 45 references, cited by 1 paper here."
authors: ["Brielen Madureira", "Mariana Madruga de Brito", "Andreas Niekler"]
year: 2026
venue: "Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing"
source: "https://aclanthology.org/2026.nlp4ecology-1.11/"
doi: "10.63317/56axeoxcmhfk"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/madureira-2026-retrieving-floods-without-floodlights-topic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/madureira-2026-retrieving-floods-without-floodlights-topic/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/16/) / Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News

# Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News

**Authors:** [Brielen Madureira](https://md.research.elamur.ai/free/en/authors/brielen-madureira/), [Mariana Madruga de Brito](https://md.research.elamur.ai/free/en/authors/mariana-madruga-de-brito/) and [Andreas Niekler](https://md.research.elamur.ai/free/en/authors/andreas-niekler/) · **Year:** 2026 · **Venue:** [Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing](https://md.research.elamur.ai/free/en/venues/nlp4ecology/) ([Workshop on Ecology, Environment, and Natural Language Processing 2026](https://md.research.elamur.ai/free/en/venues/nlp4ecology/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.nlp4ecology-1.11/) · [PDF](https://aclanthology.org/2026.nlp4ecology-1.11.pdf) · [DOI 10.63317/56axeoxcmhfk](https://doi.org/10.63317/56axeoxcmhfk) · [OpenAlex](https://openalex.org/W7166562941)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/madureira-2026-retrieving-floods-without-floodlights-topic/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Media studies of extreme climate events often build corpora by searching news archives with hazard keywords. Keyword matching recalls many documents, but it also returns many false positives. A word such as "flood" (German *Flut*, *Hochwasser*) may appear as a metaphor, inside an unrelated compound, or in talk of a merely hypothetical risk. There is usually too little annotated data to train deep classifiers from scratch. The authors therefore reuse standard topic models (LDA and NMF), with no change to their training, as binary relevance filters for German news about seven hazard types.

After training, a document is linked to a topic if that topic's share in the document reaches a threshold. Topics are then labelled relevant automatically, so no manual interpretation is needed. A topic counts as relevant if it gives a query keyword enough probability or ranks a keyword among its top terms. A small annotated sample is used only for evaluation.

For some hazards, topic models perform on par with a fine-tuned text-embedding classifier and a prompted open-weight LLM. They also tend toward higher precision and stay interpretable, while the LLM has the lowest precision.

## Key points
- **Hazards covered:** seven types of extreme climate events in German news: flood, storm, drought, wildfire, heat wave, cold wave and landslide.
- **Classification method:**
  - Uses vanilla LDA and NMF posteriors without altering the training regime.
  - Each document is linked to topics through a document–topic probability threshold θ.
  - Topics are split into relevant and irrelevant by one of two rules: "keyword proximity" (a keyword's probability in the topic exceeds γ) or "top terms" (a keyword appears among the topic's top k features).
- **Baselines:**
  - A fine-tuned text embedding classifier.
  - An open-weight LLM prompted in German with a definition and a keyword list for each hazard.
  - The LLM baseline showed the lowest precision.
- **Hazard dependence:** results differ across hazards, which the authors take as evidence against treating climate events as a single class in NLP tasks.
- **Venue:** 2nd NLP4Ecology Workshop @ LREC 2026, pp. 115–134.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Leipzig University](https://md.research.elamur.ai/free/en/universities/leipzig-university/) — University, Leipzig, Germany · 26 works · 8,622 citations
- [Helmholtz Centre for Environmental Research](https://md.research.elamur.ai/free/en/labs/helmholtz-centre-for-environmental-research/) — Research institute, Leipzig, Germany · 3 works · 1 citation

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 General Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/general-social-sciences/) · 227 works

💡 Concepts (1): [💡 Topic modeling](https://md.research.elamur.ai/free/en/concepts/topic-modeling/) · 47 works

## Cite

Cite as: Brielen Madureira, Mariana Madruga de Brito and Andreas Niekler. 2026. Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News. Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{madureira2026retrieving,
  title = {{Retrieving Floods without Floodlights: Topic Models as Binary Classifiers for Extreme Climate Events in German News}},
  author = {Brielen Madureira, Mariana Madruga {de Brito} and Andreas Niekler},
  booktitle = {Proceedings of the 2nd Workshop on Ecology, Environment, and Natural Language Processing},
  year = {2026},
  doi = {10.63317/56axeoxcmhfk},
  url = {https://doi.org/10.63317/56axeoxcmhfk}
}
```

- [← previous Retrieving Climate Change Disinformation by Narrative](https://md.research.elamur.ai/free/en/papers/upravitelev-2026-retrieving-climate-change-disinformation-narrative/)
- [next → RETUYT-INCO at BEA 2026 Shared Task 1: Feature-Enriched mDeBERTa for Word Difficulty Prediction](https://md.research.elamur.ai/free/en/papers/robaina-2026-retuyt-inco-bea-2026-shared/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/16/)

## References

45 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Pedro Henrique Lima Alencar, Jan Sodoge, Eva Nora Paton, and Mariana Madruga De Brito. 2024. Flash droughts and their impacts—using newspaper articles to assess the perceived consequences of rapidly emerging droughts. Environmental Research Letters, 19(7):074048. [↗](https://doi.org/10.1088/1748-9326/ad58fa)
2. Aditya Anantharaman, Arpit Jadiya, Chandana Tulasi Sai Siri, Bharath NVS Adikar, and Biju Mohan. 2019. Performance evaluation of topic modeling algorithms for text classification. In 2019 3rd International Conference on Trends in Electronics and Informatics (ICOEI), pages 704–708. [find](https://scholar.google.com/scholar?q=Aditya+Anantharaman%2C+Arpit+Jadiya%2C+Chandana+Tulasi+Sai+Siri%2C+Bharath+NVS+Adikar%2C+and+Biju+Mohan%2E+2019%2E+Performance+evaluation+of+topic+modeling+algorithms+for+text+classification%2E+In+2019+3rd+Internat)
3. Dimo Angelov and Diana Inkpen. 2024. Topic modeling: Contextual token embeddings are all you need. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 13528–13539, Miami, Florida, USA. Association for Computational Linguistics. [↗](https://doi.org/10.48448/xdps-7869)
4. Christina Barz, Melanie Siegel, and Daniel Hanss. 2025. Analyzing the online communication of environmental movement organizations: NLP approaches to topics, sentiment, and emotions. In Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025), pages 68–76, Tallinn, Estonia. University of Tartu Library. [find](https://scholar.google.com/scholar?q=Christina+Barz%2C+Melanie+Siegel%2C+and+Daniel+Hanss%2E+2025%2E+Analyzing+the+online+communication+of+environmental+movement+organizations%3A+NLP+approaches+to+topics%2C+sentiment%2C+and+emotions%2E+In+Proceedings+of)
5. Valentina Tretti Beckles and Adrian Vergara Heidke. 2025. Thematic categorization on pineapple production in Costa Rica: An exploratory analysis through topic modeling. In Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025), pages 44–55, Tallinn, Estonia. University of Tartu Library. [find](https://scholar.google.com/scholar?q=Valentina+Tretti+Beckles+and+Adrian+Vergara+Heidke%2E+2025%2E+Thematic+categorization+on+pineapple+production+in+Costa+Rica%3A+An+exploratory+analysis+through+topic+modeling%2E+In+Proceedings+of+the+1st+Works)
6. David M. Blei, Andrew Y. Ng, and Michael I. Jordan. 2003. [Latent dirichlet allocation](https://md.research.elamur.ai/free/en/papers/blei-2003-latent-dirichlet-allocation/). The Journal of Machine Learning Research, 3:993–1022.
7. Erica Cai, Xi Chen, Reagan Grey Keeney, Ethan Zuckerman, Brendan O’Connor, and Przemyslaw A. Grabowicz. 2025. Identifying and investigating global news coverage of critical events such as disasters and terrorist attacks. Proceedings of the International AAAI Conference on Web and Social Media, 19(1):307–323. [find](https://scholar.google.com/scholar?q=Erica+Cai%2C+Xi+Chen%2C+Reagan+Grey+Keeney%2C+Ethan+Zuckerman%2C+Brendan+O%E2%80%99Connor%2C+and+Przemyslaw+A%2E+Grabowicz%2E+2025%2E+Identifying+and+investigating+global+news+coverage+of+critical+events+such+as+disasters+an)
8. Tais Maria Nunes Carvalho, Andreas Niekler, Christian Kuhlicke, Jakob Zscheischler, and Mariana Madruga de Brito. 2025. Global synthesis of peer-reviewed articles reveals blind spots in climate impacts research. Preprint, available at Research Square. [↗](https://doi.org/10.21203/rs.3.rs-6095740/v1)
9. Jianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo, Defu Lian, and Zheng Liu. 2024. [M3-embedding: Multi-linguality, multi-functionality, multi-granularity text embeddings through self-knowledge distillation](https://md.research.elamur.ai/free/en/papers/chen-2024-m3-embedding-multi-linguality/). In Findings of the Association for Computational Linguistics: ACL 2024, pages 2318–2335, Bangkok, Thailand. Association for Computational Linguistics.
10. Xingyuan Chen, Yunqing Xia, Peng Jin, and John Carroll. 2015. Dataless text classification with descriptive lda. Proceedings of the AAAI Conference on Artificial Intelligence, 29(1). [find](https://scholar.google.com/scholar?q=Xingyuan+Chen%2C+Yunqing+Xia%2C+Peng+Jin%2C+and+John+Carroll%2E+2015%2E+Dataless+text+classification+with+descriptive+lda%2E+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+29%281%29%2E)
11. Damien Delforge, Valentin Wathelet, Regina Below, Cinzia Lanfredi Sofia, Margo Tonnelier, Joris A.F. van Loenhout, and Niko Speybroeck. 2025. Em-dat: the emergency events database. International Journal of Disaster Risk Reduction, 124:105509. [↗](https://doi.org/10.1016/j.ijdrr.2025.105509)
12. Shusei Eshima, Kosuke Imai, and Tomoya Sasaki. 2024. Keyword-assisted topic models. American Journal of Political Science, 68(2):730–750. [↗](https://doi.org/10.1111/ajps.12779)
13. Melanie Gall, Kevin A. Borden, and Susan L. Cutter. 2009. When do losses count?: Six fallacies of natural hazards loss data. Bulletin of the American Meteorological Society, 90(6):799 – 810. [find](https://scholar.google.com/scholar?q=Melanie+Gall%2C+Kevin+A%2E+Borden%2C+and+Susan+L%2E+Cutter%2E+2009%2E+When+do+losses+count%3F%3A+Six+fallacies+of+natural+hazards+loss+data%2E+Bulletin+of+the+American+Meteorological+Society%2C+90%286%29%3A799+%E2%80%93+810%2E)
14. Ryan J. Gallagher, Kyle Reing, David Kale, and Greg Ver Steeg. 2017. Anchored correlation explanation: Topic modeling with minimal domain knowledge. Transactions of the Association for Computational Linguistics, 5:529–542. [↗](https://doi.org/10.1162/tacl_a_00078)
15. Francesca Grasso, Ronny Patz, and Manfred Stede. 2024. NYTAC-CC: A climate change subcorpus of New York Times articles. In Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024), pages 403–409, Pisa, Italy. CEUR Workshop Proceedings. [find](https://scholar.google.com/scholar?q=Francesca+Grasso%2C+Ronny+Patz%2C+and+Manfred+Stede%2E+2024%2E+NYTAC%2DCC%3A+A+climate+change+subcorpus+of+New+York+Times+articles%2E+In+Proceedings+of+the+Tenth+Italian+Conference+on+Computational+Linguistics+%28CLi)
16. Swapnil Hingmire, Sandeep Chougule, Girish K. Palshikar, and Sutanu Chakraborti. 2013. Document classification by topic labeling. SIGIR ’13, page 877–880, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Swapnil+Hingmire%2C+Sandeep+Chougule%2C+Girish+K%2E+Palshikar%2C+and+Sutanu+Chakraborti%2E+2013%2E+Document+classification+by+topic+labeling%2E+SIGIR+%E2%80%9913%2C+page+877%E2%80%93880%2C+New+York%2C+NY%2C+USA%2E+Association+for+Computing+)
17. Rebecca Louise Jones, Aditi Kharb, and Sandy Tubeuf. 2023. The untold story of missing data in disaster research: a systematic review of the empirical literature utilising the emergency events database (em-dat). Environmental Research Letters, 18(10):103006. [↗](https://doi.org/10.1088/1748-9326/acfd42)
18. Inhye Kong and Ross S. Purves. 2026. Analyzing geographic bias of newspaper articles reporting global climate disasters. Annals of the American Association of Geographers, 116(2):270–288. [↗](https://doi.org/10.1080/24694452.2025.2564220)
19. Murathan Kurfali, Shorouq Zahra, Joakim Nivre, and Gabriele Messori. 2025. ClimateEval: A comprehensive benchmark for NLP tasks related to climate change. In Proceedings of the 2nd Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2025), pages 194–207, Vienna, Austria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Murathan+Kurfali%2C+Shorouq+Zahra%2C+Joakim+Nivre%2C+and+Gabriele+Messori%2E+2025%2E+ClimateEval%3A+A+comprehensive+benchmark+for+NLP+tasks+related+to+climate+change%2E+In+Proceedings+of+the+2nd+Workshop+on+Natural)
20. Markus Leippold and Francesco Saverio Varini. 2020. Climatext: A dataset for climate change topic detection. In NeurIPS 2020 Workshop on Tackling Climate Change with Machine Learning. [find](https://scholar.google.com/scholar?q=Markus+Leippold+and+Francesco+Saverio+Varini%2E+2020%2E+Climatext%3A+A+dataset+for+climate+change+topic+detection%2E+In+NeurIPS+2020+Workshop+on+Tackling+Climate+Change+with+Machine+Learning%2E)
21. Alexandra Lesnikowski, Ella Belfer, Emma Rodman, Julie Smith, Robbert Biesbroek, John D. Wilkerson, James D. Ford, and Lea Berrang-Ford. 2019. Frontiers in data analytics for adaptation research: Topic modeling. WIREs Climate Change, 10(3):e576. [↗](https://doi.org/10.1002/wcc.576)
22. Chenliang Li, Jian Xing, Aixin Sun, and Zongyang Ma. 2016a. Effective document labeling with very few seed words: A topic model approach. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, CIKM ’16, page 85–94, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Chenliang+Li%2C+Jian+Xing%2C+Aixin+Sun%2C+and+Zongyang+Ma%2E+2016a%2E+Effective+document+labeling+with+very+few+seed+words%3A+A+topic+model+approach%2E+In+Proceedings+of+the+25th+ACM+International+on+Conference+on+)
23. N. Li, W. Thiery, S. Zahra, M. Madruga de Brito, K. Worou, M. Kurfalı, S. Lampe, P. Muñoz, C. Flynn, C. Trigoso, J. Nivre, J. Zscheischler, and G. Messori. 2025. Wikimpacts 1.0: A new global climate impact database based on automated information extraction from wikipedia. EGUsphere, 2025:1–43. [↗](https://doi.org/10.5194/nhess-26-2609-2026)
24. Ni Li, Shorouq Zahra, Mariana Brito, Clare Flynn, Olof Görnerup, Koffi Worou, Murathan Kurfali, Chanjuan Meng, Wim Thiery, Jakob Zscheischler, Gabriele Messori, and Joakim Nivre. 2024. Using LLMs to build a database of climate extreme impacts. In Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024), pages 93– 110, Bangkok, Thailand. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Ni+Li%2C+Shorouq+Zahra%2C+Mariana+Brito%2C+Clare+Flynn%2C+Olof+G%C3%B6rnerup%2C+Koffi+Worou%2C+Murathan+Kurfali%2C+Chanjuan+Meng%2C+Wim+Thiery%2C+Jakob+Zscheischler%2C+Gabriele+Messori%2C+and+Joakim+Nivre%2E+2024%2E+Using+LLMs+to+b)
25. Ximing Li, Changchun Li, Jinjin Chi, Jihong Ouyang, and Chenliang Li. 2018. Dataless text classification: A topic modeling approach with document manifold. CIKM ’18, page 973–982, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Ximing+Li%2C+Changchun+Li%2C+Jinjin+Chi%2C+Jihong+Ouyang%2C+and+Chenliang+Li%2E+2018%2E+Dataless+text+classification%3A+A+topic+modeling+approach+with+document+manifold%2E+CIKM+%E2%80%9918%2C+page+973%E2%80%93982%2C+New+York%2C+NY%2C+USA%2E+A)
26. Zhenzhong Li, Wenqian Shang, and Menghan Yan. 2016b. News text classification model based on topic model. In 2016 IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS), pages 1–5. [find](https://scholar.google.com/scholar?q=Zhenzhong+Li%2C+Wenqian+Shang%2C+and+Menghan+Yan%2E+2016b%2E+News+text+classification+model+based+on+topic+model%2E+In+2016+IEEE%2FACIS+15th+International+Conference+on+Computer+and+Information+Science+%28ICIS%29%2C+pa)
27. Mariana Madruga de Brito, Jan Sodoge, Heidi Kreibich, and Christian Kuhlicke. 2024. Comprehensive assessment of flood socioeconomic impacts through text-mining. Water Resources Research, 61(1). [↗](https://doi.org/10.1029/2024wr037813)
28. Mariana Madruga de Brito, Jan Sodoge, Heidi Kreibich, and Christian Kuhlicke. 2025. Comprehensive assessment of flood socioeconomic impacts through text-mining. Water Resources Research, 61(1):e2024WR037813. [↗](https://doi.org/10.1029/2024wr037813)
29. Daniel Maier, Annie Waldherr, Peter Miltner, Gregor Wiedemann, Andreas Niekler, Alexa Keinert, Barbara Pfetsch, Gerhard Heyer, Ueli Reber, Thomas Häussler, et al. 2021. Applying lda topic modeling in communication research: Toward a valid and reliable methodology. In Computational methods for communication science, pages 13– 38. Routledge. [find](https://scholar.google.com/scholar?q=Daniel+Maier%2C+Annie+Waldherr%2C+Peter+Miltner%2C+Gregor+Wiedemann%2C+Andreas+Niekler%2C+Alexa+Keinert%2C+Barbara+Pfetsch%2C+Gerhard+Heyer%2C+Ueli+Reber%2C+Thomas+H%C3%A4ussler%2C+et+al%2E+2021%2E+Applying+lda+topic+modeling+in+)
30. Jon Mcauliffe and David Blei. 2007. Supervised topic models. In Advances in Neural Information Processing Systems, volume 20. Curran Associates, Inc. [find](https://scholar.google.com/scholar?q=Jon+Mcauliffe+and+David+Blei%2E+2007%2E+Supervised+topic+models%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+20%2E+Curran+Associates%2C+Inc%2E)
31. Timothy Miller, Dmitriy Dligach, and Guergana Savova. 2016. Unsupervised document classification with informed topic models. In Proceedings of the 15th Workshop on Biomedical Natural Language Processing, pages 83–91, Berlin, Germany. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Timothy+Miller%2C+Dmitriy+Dligach%2C+and+Guergana+Savova%2E+2016%2E+Unsupervised+document+classification+with+informed+topic+models%2E+In+Proceedings+of+the+15th+Workshop+on+Biomedical+Natural+Language+Processi)
32. Taís Maria Nunes Carvalho, Francisco De Assis De Souza Filho, and Mariana Madruga De Brito. 2024. Unveiling water allocation dynamics: a text analysis of 25 years of stakeholder meetings. Environmental Research Letters, 19(4):044066. [↗](https://doi.org/10.1088/1748-9326/ad37cd)
33. Aytuğ Onan, Serdar Korukoğlu, and Hasan Bulut. 2016. Ensemble of keyword extraction methods and classifiers in text classification. Expert Systems with Applications, 57:232–247. [↗](https://doi.org/10.1016/j.eswa.2016.03.045)
34. Telma Peura, Attila Krizsán, Salla-Riikka Kuusalu, and Veronika Laippala. 2025. Perspectives on forests and forestry in Finnish online discussions - a topic modeling approach to suomi24. In Proceedings of the 1st Workshop on Ecology, Environment, and Natural Language Processing (NLP4Ecology2025), pages 10–15, Tallinn, Estonia. University of Tartu Library. [find](https://scholar.google.com/scholar?q=Telma+Peura%2C+Attila+Krizs%C3%A1n%2C+Salla%2DRiikka+Kuusalu%2C+and+Veronika+Laippala%2E+2025%2E+Perspectives+on+forests+and+forestry+in+Finnish+online+discussions+%2D+a+topic+modeling+approach+to+suomi24%2E+In+Proceeding)
35. Nils Reimers and Iryna Gurevych. 2019. [Sentence-BERT: Sentence embeddings using Siamese BERT-networks](https://md.research.elamur.ai/free/en/papers/reimers-2019-sentence-bert-sentence-embeddings-siamese/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992, Hong Kong, China. Association for Computational Linguistics. [↗](https://doi.org/10.18653/v1/d19-1410)
36. Timothy N Rubin, America Chambers, Padhraic Smyth, and Mark Steyvers. 2012. Statistical topic models for multi-label document classification. Machine learning, 88(1):157–208. [↗](https://doi.org/10.1007/s10994-011-5272-5)
37. Efsun Sarioglu, Kabir Yadav, and Hyeong-Ah Choi. 2013. Topic modeling based classification of clinical reports. In 51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop, pages 67–73, Sofia, Bulgaria. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Efsun+Sarioglu%2C+Kabir+Yadav%2C+and+Hyeong%2DAh+Choi%2E+2013%2E+Topic+modeling+based+classification+of+clinical+reports%2E+In+51st+Annual+Meeting+of+the+Association+for+Computational+Linguistics+Proceedings+of+t)
38. Christopher Schröder, Lydia Müller, Andreas Niekler, and Martin Potthast. 2023. Small-text: Active learning for text classification in python. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 84– 95, Dubrovnik, Croatia. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Christopher+Schr%C3%B6der%2C+Lydia+M%C3%BCller%2C+Andreas+Niekler%2C+and+Martin+Potthast%2E+2023%2E+Small%2Dtext%3A+Active+learning+for+text+classification+in+python%2E+In+Proceedings+of+the+17th+Conference+of+the+European+Cha)
39. Christopher Schröder and Andreas Niekler. 2020. A survey of active learning for text classification using deep neural networks. ArXiv preprint: 2008.07267. [↗](https://arxiv.org/abs/2008.07267)
40. Sattar Seifollahi, Massimo Piccardi, and Alireza Jolfaei. 2021. An embedding-based topic model for document classification. ACM Trans. Asian Low-Resour. Lang. Inf. Process., 20(3). [↗](https://doi.org/10.1145/3431728)
41. Jan Sodoge, Christian Kuhlicke, and Mariana Madruga De Brito. 2023. Automatized spatiotemporal detection of drought impacts from newspaper articles using natural language processing and machine learning. Weather and Climate Extremes, 41:100574. [find](https://scholar.google.com/scholar?q=Jan+Sodoge%2C+Christian+Kuhlicke%2C+and+Mariana+Madruga+De+Brito%2E+2023%2E+Automatized+spatiotemporal+detection+of+drought+impacts+from+newspaper+articles+using+natural+language+processing+and+machine+learni)
42. Manfred Stede, Yannic Bracke, Luka Borec, Neele Charlotte Kinkel, and Maria Skeppstedt. 2023. Framing climate change in nature and science editorials: applications of supervised and unsupervised text categorization. Journal of Computational Social Science, 6(2):485–513. [↗](https://doi.org/10.1007/s42001-023-00199-7)
43. Lewis Tunstall, Nils Reimers, Unso Eun Seo Jo, Luke Bates, Daniel Korat, Moshe Wasserblat, and Oren Pereg. 2022. Efficient few-shot learning without prompts. ArXiv preprint: 2209.11055. [↗](https://arxiv.org/abs/2209.11055)
44. Kerstin K Zander, Hunter S Baggen, and Stephen T Garnett. 2023. Topic modelling the mobility response to heat and drought. Climatic Change, 176(4):42. [↗](https://doi.org/10.1007/s10584-023-03524-1)
45. Daochen Zha and Chenliang Li. 2019. Multi-label dataless text classification with topic modeling. Knowledge and Information Systems, 61(1):137– 160. [↗](https://doi.org/10.1007/s10115-018-1280-0)

*Updated 1 November 2026*