---
title: "Uot1 at FIGNEWS 2024 Shared Task: Labeling News Bias (2024)"
description: "The University of Tripoli team (UoT1) took part in the bias subtask of FIGNEWS 2024. 15 references, cited by 1 paper here."
authors: ["Abdusalam Nwesri", "Mai Elbaabaa", "Fatima Lashihar", "Fatma Alalos"]
year: 2024
venue: "Proceedings of the Second Arabic Natural Language Processing Conference"
source: "https://aclanthology.org/2024.arabicnlp-1.60/"
doi: "10.18653/v1/2024.arabicnlp-1.60"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/nwesri-2024-uot1-fignews-2024-shared-task/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/nwesri-2024-uot1-fignews-2024-shared-task/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2024](https://md.research.elamur.ai/free/en/papers/2024/page/14/) / Uot1 at FIGNEWS 2024 Shared Task: Labeling News Bias

# Uot1 at FIGNEWS 2024 Shared Task: Labeling News Bias

**Authors:** [Abdusalam Nwesri](https://md.research.elamur.ai/free/en/authors/abdusalam-f-ahmad-nwesri/), Mai Elbaabaa, Fatima Lashihar and Fatma Alalos · **Year:** 2024 · **Venue:** [Proceedings of the Second Arabic Natural Language Processing Conference](https://md.research.elamur.ai/free/en/venues/arabicnlp/) ([ArabicNLP 2024](https://md.research.elamur.ai/free/en/venues/arabicnlp/2024/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2024.arabicnlp-1.60/) · [PDF](https://aclanthology.org/2024.arabicnlp-1.60.pdf) · [DOI 10.18653/v1/2024.arabicnlp-1.60](https://doi.org/10.18653/v1/2024.arabicnlp-1.60) · [OpenAlex](https://openalex.org/W4402671317)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/nwesri-2024-uot1-fignews-2024-shared-task/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The University of Tripoli team (UoT1) took part in the bias subtask of FIGNEWS 2024. The task asked teams to write annotation guidelines for labeling bias in multilingual news about the 2023–2024 Gaza–Israel war, and to apply them. The organizers supplied 15,000 articles in English, Arabic, Hebrew, French and Hindi, each also machine-translated into English and Arabic. Eight software-engineering staff, two of them experienced annotators, worked mostly from the Arabic translations. They found the shared spreadsheet awkward for long texts, so they built their own annotation tool. It shows annotator agreement and per-person counts on a dashboard, and it hides articles once they are labeled. Using it, the team labeled 3,900 articles. They ranked 4th in quality (macro F1 48.7), 6th in centrality by macro F1 and 4th by kappa, 7th in quantity, and 9th for guidelines. The paper's main value is practical: a record of what goes wrong in bias annotation, such as annotator fatigue, translation artifacts, and label sets that cannot express one-sided support.

## Key points
- The FIGNEWS 2024 data has 15 batches of 1,000 articles. Each batch splits into a 100-article IAA subset that every annotator labels and a 900-article MAIN subset that the team shares.
- The organizers' bias labels included Unbiased, Biased against Palestine, Biased against Israel, against both, against others, Unclear and Not Applicable.
  - UoT1 added two labels: "Biased in Favour of Israel" and "Biased in Favour of Palestine".
  - The organizers later required the team to drop these labels and re-annotate.
- Agreement was tracked visually on the tool's dashboard rather than with a computed statistic. Annotators disagreed moderately, and they agreed most often on "Unbiased", then on "Biased against Palestine".
- Results:
  - quality track: macro F1 48.7, 4th place;
  - centrality track: 6th by macro F1, 4th by kappa;
  - quantity track: 3,900 points, 7th place;
  - guidelines: 9th place.
- The paper reports participant numbers inconsistently: 16 teams in one place, and 23 participating with 17 qualifying in another.

## Interesting ideas
- Some texts support one side without attacking the other, and a label set built only on "against X" cannot express that; adding "in favour of X" labels separates stance direction from stance target.
- Machine translation turned the name "Hamas" into the Arabic common noun for "enthusiasm", which misled annotators; a proper-noun versus common-word confusion like this silently corrupts meaning downstream.
- A live dashboard of who agreed on which item let disagreements be seen and discussed without first computing a formal metric.
- The tool presents only unlabeled items and hides each one once it is done, so shared annotation proceeds without duplicated work.
- The authors argue that raw quantity rankings are unfair when team sizes range from 2 to 21, and that output should be normalized per annotator.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (frames): Speech-act and stance frames could record polarity (support vs attack) separately from the target, so praise of A is not forced into a reading of hostility toward B.
- **I2** (tokens): The tagger could flag capitalized tokens that also exist as ordinary lexemes and keep both PROPN and NOUN readings alive until the tree and the world resolve which one fits.
- **I3** (learn): A per-sentence view of where the witness parsers disagree would point quickly to the constructions that need repair rules or teacher review.
- **I4** (learn): The silver-data or LLM-teacher queue could expose only unresolved sentences to each worker, which would cut repeated effort when several teachers run in parallel.
- **I5** (learn): Evaluations comparing witness parsers or teacher tiers could report yield per unit of cost, not totals, so cheap and expensive sources are compared fairly.

*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

- [University of Tripoli](https://md.research.elamur.ai/free/en/universities/university-of-tripoli/) — University, Tripoli, Libya · 5 works · 8 citations

📚 Shelves (4): [🖥️ 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 · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,772 works · [🤝 Sociology and Political Science](https://md.research.elamur.ai/free/en/shelves/social-sciences/sociology-and-political-science/) · 577 works

🧭 Topics (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Abdusalam Nwesri, Mai Elbaabaa, Fatima Lashihar and Fatma Alalos. 2024. Uot1 at FIGNEWS 2024 Shared Task: Labeling News Bias. Proceedings of the Second Arabic Natural Language Processing Conference.

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

```bibtex
@inproceedings{nwesri2024uot1,
  title = {{Uot1 at FIGNEWS 2024 Shared Task: Labeling News Bias}},
  author = {Abdusalam Nwesri, Mai Elbaabaa, Fatima Lashihar and Fatma Alalos},
  booktitle = {Proceedings of the Second Arabic Natural Language Processing Conference},
  year = {2024},
  doi = {10.18653/v1/2024.arabicnlp-1.60},
  url = {https://doi.org/10.18653/v1/2024.arabicnlp-1.60}
}
```

- [← previous Universal Dependencies for Saraiki](https://md.research.elamur.ai/free/en/papers/alam-2024-universal-dependencies-saraiki/)
- [next → Utilizing Game-Based Learning Baamboozle in Developing Students’ English Grammar Mastery](https://md.research.elamur.ai/free/en/papers/sakdiyah-2024-utilizing-game-based-learning-baamboozle/)
- [↑ back to papers of 2024](https://md.research.elamur.ai/free/en/papers/2024/page/14/)

## References

15 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Afra Feyza Akyürek, Lei Guo, Randa Elanwar, Prakash Ishwar, Margrit Betke, and Derry Tanti Wijaya. 2020. Multi-label and multilingual news framing analysis. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8614– 8624, Online. Association for Computational Linguistics. [↗](https://doi.org/10.60692/ynpsa-ht092)
2. Wael Al-Sarraj and Mohammed Lubbad. 2018. Bias detection of palestinian/israeli conflict in western media: A sentiment analysis experimental study. pages 98–103. [find](https://scholar.google.com/scholar?q=Wael+Al%2DSarraj+and+Mohammed+Lubbad%2E+2018%2E+Bias+detection+of+palestinian%2Fisraeli+conflict+in+western+media%3A+A+sentiment+analysis+experimental+study%2E+pages+98%E2%80%93103%2E)
3. Eric Baumer, Elisha Elovic, Ying Qin, Francesca Polletta, editor = "Mihalcea Rada Gay, Geri", Joyce Chai, and Anoop Sarkar. 2015. Testing and comparing computational approaches for identifying the lan-Robert M Entman. 2007. Framing bias: Media in the distribution of power. Journal of communication, 57(1):163–173. [find](https://scholar.google.com/scholar?q=Eric+Baumer%2C+Elisha+Elovic%2C+Ying+Qin%2C+Francesca+Polletta%2C+editor+%3D+%22Mihalcea+Rada+Gay%2C+Geri%22%2C+Joyce+Chai%2C+and+Anoop+Sarkar%2E+2015%2E+Testing+and+comparing+computational+approaches+for+identifying+the+lan)
4. Lisa Fan, Marshall White, Eva Sharma, Ruisi Su, Prafulla Kumar Choubey, Ruihong Huang, and Lu Wang. 2019. In plain sight: Media bias through the lens of factual reporting. 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 6343–6349, Hong Kong, China. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Lisa+Fan%2C+Marshall+White%2C+Eva+Sharma%2C+Ruisi+Su%2C+Prafulla+Kumar+Choubey%2C+Ruihong+Huang%2C+and+Lu+Wang%2E+2019%2E+In+plain+sight%3A+Media+bias+through+the+lens+of+factual+reporting%2E+In+Proceedings+of+the+2019+C)
5. Jonatas Grosman, Pedro Thompson, Ariane Rodrigues, Guilherme Schardong, Simone Barbosa, and Hélio Lopes. 2020. Eras: Improving the quality control in the annotation process for natural language processing tasks. Information Systems, 93:101553. [↗](https://doi.org/10.1016/j.is.2020.101553)
6. Felix Hamborg, Anastasia Zhukova, and Bela Gipp. 2019. Automated identification of media bias by word choice and labeling in news articles. [find](https://scholar.google.com/scholar?q=Felix+Hamborg%2C+Anastasia+Zhukova%2C+and+Bela+Gipp%2E+2019%2E+Automated+identification+of+media+bias+by+word+choice+and+labeling+in+news+articles%2E)
7. Sora Lim, Adam Jatowt, Michael Färber, and Masatoshi Yoshikawa. 2020. Annotating and analyzing biased sentences in news articles using crowdsourcing. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 1478–1484, Marseille, France. European Language Resources Association. [find](https://scholar.google.com/scholar?q=Sora+Lim%2C+Adam+Jatowt%2C+Michael+F%C3%A4rber%2C+and+Masatoshi+Yoshikawa%2E+2020%2E+Annotating+and+analyzing+biased+sentences+in+news+articles+using+crowdsourcing%2E+In+Proceedings+of+the+Twelfth+Language+Resources+a)
8. Sora Lim, Adam Jatowt, and Masatoshi Yoshikawa. 2018. Understanding characteristics of biased sentences in news articles. In CIKM Workshops, volume 2482 of CEUR Workshop Proceedings. CEUR-WS.org. [find](https://scholar.google.com/scholar?q=Sora+Lim%2C+Adam+Jatowt%2C+and+Masatoshi+Yoshikawa%2E+2018%2E+Understanding+characteristics+of+biased+sentences+in+news+articles%2E+In+CIKM+Workshops%2C+volume+2482+of+CEUR+Workshop+Proceedings%2E+CEUR%2DWS%2Eorg%2E)
9. Fred Morstatter, Liang Wu, Uraz Yavanoglu, Stephen Corman, and Huan Liu. 2018. Identifying framing bias in online news. ACM Transactions on Social Computing, 1:1–18. [↗](https://doi.org/10.1145/3204948)
10. Souneil Park, Seungwoo Kang, Sangyoung Chung, and Junehwa Song. 2009. Newscube: Delivering multiple aspects of news to mitigate media bias. pages 443–452. [find](https://scholar.google.com/scholar?q=Souneil+Park%2C+Seungwoo+Kang%2C+Sangyoung+Chung%2C+and+Junehwa+Song%2E+2009%2E+Newscube%3A+Delivering+multiple+aspects+of+news+to+mitigate+media+bias%2E+pages+443%E2%80%93452%2E)
11. Timo Spinde, Jan-David Krieger, Manuel Plank, and Bela Gipp. 2021a. Towards A reliable ground-truth for biased language detection. CoRR, abs/2112.07421. [↗](https://arxiv.org/abs/2112.07421)
12. Timo Spinde, Kanishka Sinha, Norman Meuschke, and Bela Gipp. 2021b. TASSY - A text annotation survey system. CoRR, abs/2112.07391. [↗](https://arxiv.org/abs/2112.07391)
13. Robert Vaagan, Frøydis Johannessen, and Marie Walsøe. 2010. Tv news and “white voices”: Dagsrevyen’s coverage of the gaza war. javnost - the Public, 17(3):39–56. [find](https://scholar.google.com/scholar?q=Robert+Vaagan%2C+Fr%C3%B8ydis+Johannessen%2C+and+Marie+Wals%C3%B8e%2E+2010%2E+Tv+news+and+%E2%80%9Cwhite+voices%E2%80%9D%3A+Dagsrevyen%E2%80%99s+coverage+of+the+gaza+war%2E+javnost+%2D+the+Public%2C+17%283%29%3A39%E2%80%9356%2E)
14. Tatiana Varacheva and Sergiu Gherghina. 2018. Neutral or biased? the presentation of the kyrgyzstan and egypt uprisings by ria novosti. Europe-Asia Studies, 70:1–23. [↗](https://doi.org/10.1080/09668136.2018.1508644)
15. Wajdi Zaghouani, Mustafa Jarrar, Nizar Habash, Houda Bouamor, Imed Zitouni, Mona Diab, Samhaa R. El-Beltagy, and Muhammed AbuOdeh, editors. 2024. [The FIGNEWS Shared Task on News Media Narratives](https://md.research.elamur.ai/free/en/papers/zaghouani-2024-fignews-shared-task-news-media/). Association for Computational Linguistics, Bangkok, Thailand.

*Updated 1 November 2026*