Skip to content

climatesense-project/climatesense-checkthat2025

Repository files navigation

🪸 ClimateSense CheckThat! 2025

Task 1 consists in distinguishing whether a sentence from a news article expresses the subjective view of the author behind it or presents an objective view on the covered topic instead.

Task 4 consists of two subtasks:

  • Subtask 4a (Scientific Web Discourse Detection): Given a social media post (tweet), detect if it contains (1) a scientific claim, (2) a reference to a scientific study / publication, or (3) mentions of scientific entities, e.g. a university or scientist.
  • Subtask 4b (Scientific Claim Source Retrieval): Given an implicit reference to a scientific paper, i.e., a social media post (tweet) that mentions a research publication without a URL, retrieve the mentioned paper from a pool of candidate papers.

Challenge website: https://checkthat.gitlab.io/clef2025/task4/

Challenge GitLab: https://gitlab.com/checkthat_lab/clef2025-checkthat-lab

⚙️ Code Style

  • Package management with Poetry (install poetry, then poetry install) then poetry shell to activate the virtual environment).
  • Semantic versioning using Semantic Release.
  • Commit messages using Conventional Commits (make sure your commit messages are formatted correctly).
  • Use commitzen to create commit messages (install commitizen, then git cz to create a commit message).

📦 Resources

🛠️ Approaches

Citation

If you use this software, please cite (bib file):

Grégoire Burel, Pasquale Lisena, Enrico Daga, Raphael Troncy, Harith Alani. 
ClimateSense at CheckThat! 2025: Combining Fine-tuned Large Language Models and Conventional Machine Learning Models for Subjectivity and Scientific Web - Discourse Analysis.
In: CLEF 2025 Working Notes, Ceur-WS Sep 2025, Madrid, Spain.

About

ClimateSense's code for CheckThat! 2025

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Contributors 3

  •  
  •  
  •