PulseAugur
LIVE 08:00:57
research · [4 sources] ·
0
research

NLP tools compare toponym identification and topic models for climate event news

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 4 sources

Two new research papers explore natural language processing techniques for analyzing news coverage of extreme climate events in German media. One paper compares the performance of off-the-shelf Named Entity Recognition (NER) tools like Flair, Spacy, and Stanza for identifying toponyms and geolocating events. The second paper investigates using Topic Models as binary classifiers to refine the retrieval of relevant news articles, comparing this approach to fine-tuned text embedding classifiers and an open-weight LLM. AI

Summary written by gemini-2.5-flash-lite from 4 sources. How we write summaries →

IMPACT These methods could improve the accuracy and efficiency of analyzing media coverage for climate impact studies.

RANK_REASON Two arXiv papers present novel NLP methods for analyzing climate event news.

Read on arXiv cs.CL →

COVERAGE [4]

  1. arXiv cs.CL TIER_1 · Brielen Madureira, Mariana Madruga de Brito, Andreas Niekler ·

    Geolocating News about Extreme Climate Events: A Comparative Analysis of Off-the-Shelf Tools for Toponym Identification in German

    arXiv:2605.03414v1 Announce Type: new Abstract: Determining the geolocation of extreme climate events and disasters in texts is a common problem in climate impact and adaptation research. Named-entity recognition (NER) tools are typically used to identify a pool of toponyms that …

  2. arXiv cs.CL TIER_1 · Brielen Madureira, Mariana Madruga de Brito, Andreas Niekler ·

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

    arXiv:2605.03450v1 Announce Type: new Abstract: In studies of media coverage of extreme climate events, NLP methods have become indispensable for identifying relevant texts in large news databases. Still, enough annotated data to train accurate deep learning-based classifiers fro…

  3. arXiv cs.CL TIER_1 · Andreas Niekler ·

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

    In studies of media coverage of extreme climate events, NLP methods have become indispensable for identifying relevant texts in large news databases. Still, enough annotated data to train accurate deep learning-based classifiers from scratch is often not available. Topic Models h…

  4. arXiv cs.CL TIER_1 · Andreas Niekler ·

    Geolocating News about Extreme Climate Events: A Comparative Analysis of Off-the-Shelf Tools for Toponym Identification in German

    Determining the geolocation of extreme climate events and disasters in texts is a common problem in climate impact and adaptation research. Named-entity recognition (NER) tools are typically used to identify a pool of toponyms that serve as candidate event locations. In this stud…

RELATED ENTITIES

RELATED TOPICS