---
title: "Mawqif-XT — paper by Albalawi et al. (2026)"
description: "The authors built Mawqif-XT, a test-only extension of 996 Arabic tweets from X on three new targets. 18 references, cited by 1 paper here."
authors: ["Rasha Albalawi", "Nuha Albadi", "Hamzah Luqman", "Maram Kurdi", "Saad Ezzini", "Asma Yamani", "Ahmed Ashraf"]
year: 2026
venue: "arXiv:2608.09539"
source: "https://arxiv.org/abs/2608.09539"
doi: "10.48550/arxiv.2608.09539"
arxiv: "2608.09539"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/albalawi-2026-mawqif-xt-arabic-benchmark-dataset/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/albalawi-2026-mawqif-xt-arabic-benchmark-dataset/)

[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/14/) / Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection

# Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection

**Authors:** Rasha Albalawi, [Nuha Albadi](https://md.research.elamur.ai/free/en/authors/nuha-albadi/), [Hamzah Luqman](https://md.research.elamur.ai/free/en/authors/hamzah-luqman/), [Maram Kurdi](https://md.research.elamur.ai/free/en/authors/maram-kurdi/), [Saad Ezzini](https://md.research.elamur.ai/free/en/authors/saad-ezzini/), [Asma Yamani](https://md.research.elamur.ai/free/en/authors/asma-yamani/) and [Ahmed Ashraf](https://md.research.elamur.ai/free/en/authors/ahmed-ashraf/) · **Year:** 2026 · **Venue:** arXiv:2608.09539 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2608.09539) · [PDF](https://arxiv.org/pdf/2608.09539) · [DOI 10.48550/arxiv.2608.09539](https://doi.org/10.48550/arxiv.2608.09539) · [arXiv 2608.09539](https://arxiv.org/abs/2608.09539) · [OpenAlex](https://openalex.org/W7202208809)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [1](https://md.research.elamur.ai/free/en/papers/albalawi-2026-mawqif-xt-arabic-benchmark-dataset/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Arabic has few public resources for checking whether a stance classifier still works when the discussion topic changes. The original Mawqif corpus labels tweets for stance, sentiment, and sarcasm, but its targets are fixed, so it cannot measure transfer to new topics. The authors built Mawqif-XT, a test-only extension of 996 Arabic tweets from X on three new targets. Women Driving is close in theme to the existing Women Empowerment target. E-Cars and Trimester System come from unrelated domains. Each tweet was labeled by three annotators under the original Mawqif guidelines, and a fourth annotator settled disagreements. Two protocols are defined: training on the original targets and testing on the related one, or training on two original targets and testing on the unrelated ones. Baselines cover Arabic BERT encoders, multilingual encoders, and zero-shot 70B-class LLMs. Qwen 2.5 had the best overall scores, but no model won on every target. The resource gives Arabic stance research a standard, graded test of cross-target generalization.

## Key points
- Size per target: Women Driving 352 tweets (kept from a manually checked sample of 500), E-Cars 332 (from 5,006 collected), and Trimester System 312 (from 3,000 collected).
- Label sets: stance (Favor / Against / None), sentiment (Positive / Negative / Neutral), and sarcasm (Yes / No), each annotated independently. URLs and user mentions were replaced with URL and MENTION tokens.
- Overall Fleiss' Kappa reached moderate agreement on all three tasks, with values of 0.564 (stance), 0.485 (sentiment), and 0.526 (sarcasm). About two thirds of disagreements were between the neutral label and a polar one (66.12% for stance, 67.76% for sentiment).
- Protocol 1 (related target, F avg2): Qwen 2.5 (72B) scored best on Women Driving with 73.66. The strongest encoder there was AraBERT-v02 with 65.92.
- Protocol 2 (unseen targets, F avg2):
  - Qwen 2.5 scored 80.60 on E-Cars and 74.75 overall.
  - MARBERT led on Trimester System with 74.11 and was the best encoder overall with 72.21.
  - Multilingual encoders (mBERT, DistilBERT-multilingual, XLM-R-base) stayed in the mid-50s.

## Interesting ideas
- The test set is graded by distance from training: one target that neighbours a training topic and two that are far away, so near transfer and far transfer are scored separately rather than blended.
- The authors classify the kinds of annotator disagreement and find most are neutral versus polar, rarely polar versus polar. This explains the moderate kappa better than the number alone.
- Stance toward a target, emotional tone, and sarcasm are labeled independently, and the paper explicitly keeps cases where stance and sentiment point in opposite directions.
- Fine-tuned small encoders and zero-shot large LLMs are scored under the same protocols, and the per-target winner changes, so no single model is best everywhere.
- Before labeling, URLs and user mentions are normalized into placeholder tokens, which removes noisy, unrepeatable strings while keeping their position in the sentence.

## For Mova

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

- **I1** (learn): Held-out evaluation could be split into genres close to the treebank sources and clearly distant ones, so that a drop in accuracy can be traced to domain distance rather than hidden in one average.
- **I2** (learn): When the witness parsers disagree on silver data, sorting the conflicts by type (label only, attachment, both) would show which disagreements are harmless boundary cases and which signal real errors.
- **I3** (frames): crate prag could store an author's position toward an entity separately from the text's polarity and the irony flag, so that a negative-sounding sarcastic sentence can still yield a supportive stance.
- **I4** (learn): LLM teacher tiers could be selected per domain or per phenomenon based on measured agreement, rather than trusting one teacher globally.
- **I5** (tokens): The en tokenizer could map URLs, handles, and similar spans to typed placeholder tokens with fixed tags, so the parser sees stable inputs on web-style text.

*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

- [King Fahd University of Petroleum and Minerals](https://md.research.elamur.ai/free/en/universities/king-fahd-university-of-petroleum-and-minerals/) — University, Dhahran, Saudi Arabia · 52 works · 4,666 citations

Also on the byline: [University of Tabuk](https://ror.org/04yej8x59).

📚 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 · [🎭 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

🧭 Topics (3): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 972 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works · [📏 Evaluation & benchmarks](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · 1,220 works

## Cite

Cite as: Rasha Albalawi, Nuha Albadi, Hamzah Luqman, Maram Kurdi, Saad Ezzini, Asma Yamani and Ahmed Ashraf. 2026. Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection. arXiv:2608.09539.

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

```bibtex
@misc{albalawi2026mawqif,
  title = {{Mawqif-XT: An Arabic Benchmark Dataset for Cross-Target Stance Detection}},
  author = {Rasha Albalawi, Nuha Albadi, Hamzah Luqman, Maram Kurdi, Saad Ezzini, Asma Yamani and Ahmed Ashraf},
  year = {2026},
  doi = {10.48550/arxiv.2608.09539},
  eprint = {2608.09539},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2608.09539}
}
```

- [← previous MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding](https://md.research.elamur.ai/free/en/papers/zhang-2026-mavis-multi-agent-video-retrieval/)
- [next → McMasters of Change: Predicting Well-Being States and Transitions from Longitudinal Language](https://md.research.elamur.ai/free/en/papers/zhang-2026-mcmasters-change-predicting-well-being/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/14/)

## References

18 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. S. Mohammad, S. Kiritchenko, P. Sobhani, X. Zhu, C. Cherry, [Semeval-2016 task 6: Detecting stance in tweets](https://md.research.elamur.ai/free/en/papers/mohammad-2016-semeval-2016-task-6-detecting/), in: Proceedings of the 10th international workshop on semantic evaluation (SemEval-2016), 2016, pp. 31–41.
2. N. S. Alturayeif, H. A. Luqman, M. A. K. Ahmed, [Mawqif: A multi-label arabic dataset for target-specific stance detection](https://md.research.elamur.ai/free/en/papers/alturayeif-2022-mawqif-multi-label-arabic-dataset/), in: Proceedings of the Seventh Arabic Natural Language Processing Workshop (WANLP), 2022, pp. 174–184.
3. R. Baly, M. Mohtarami, J. Glass, L. Màrquez, A. Moschitti, P. Nakov, [Integrating stance detection and fact checking in a unified corpus](https://md.research.elamur.ai/free/en/papers/baly-2018-integrating-stance-detection-fact-checking/), in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), 2018, pp. 21–27.
4. J. Khouja, [Stance prediction and claim verification: An arabic perspective](https://md.research.elamur.ai/free/en/papers/khouja-2020-stance-prediction-claim-verification-arabic/), in: Proceedings of the Third Workshop on Fact Extraction and VERification (FEVER), 2020, pp. 8–17.
5. T. Alhindi, A. Alabdulkarim, A. Alshehri, M. Abdul-Mageed, P. Nakov, [Arastance: A multi-country and multi-domain dataset of arabic stance detection for fact checking](https://md.research.elamur.ai/free/en/papers/alhindi-2021-arastance-multi-country-multi-domain/), in: Proceedings of the Fourth Workshop on NLP for Internet Freedom: Censorship, Disinformation, and Propaganda, 2021, pp. 57–65.
6. A. Charfi, M. Bessghaier, A. Atalla, R. Akasheh, S. Al-Emadi, W. Zaghouani, [Marasta: A multi-dialectal arabic cross-domain stance corpus](https://md.research.elamur.ai/free/en/papers/charfi-2024-marasta-multi-dialectal-arabic-cross/), in: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), 2024, pp. 11060–11069.
7. M. M. Jaziriyan, A. Akbari, H. Karbasi, [Exaasc: a general target-based stance detection corpus in arabic language](https://md.research.elamur.ai/free/en/papers/jaziriyan-2022-exaasc-general-target-based-stance/), in: 2021 11th International Conference on Computer Engineering and Knowledge (ICCKE), IEEE, 2021, pp. 424–429.
8. A. Alkhathlan, F. Alahmadi, F. Kateb, H. Al-Khalifa, Constructing and evaluating arabicstancex: A social media dataset for arabic stance detection, Frontiers in Artificial Intelligence 8 (2025) 1615800. [find](https://scholar.google.com/scholar?q=A%2E+Alkhathlan%2C+F%2E+Alahmadi%2C+F%2E+Kateb%2C+H%2E+Al%2DKhalifa%2C+Constructing+and+evaluating+arabicstancex%3A+A+social+media+dataset+for+arabic+stance+detection%2C+Frontiers+in+Artificial+Intelligence+8+%282025%29+161580)
9. J. R. Landis, G. G. Koch, The measurement of observer agreement for categorical data, biometrics (1977) 159– 174. [find](https://scholar.google.com/scholar?q=J%2E+R%2E+Landis%2C+G%2E+G%2E+Koch%2C+The+measurement+of+observer+agreement+for+categorical+data%2C+biometrics+%281977%29+159%E2%80%93+174%2E)
10. W. Antoun, F. Baly, H. Hajj, [Arabert: Transformer-based model for arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/), arXiv (2020).
11. G. Inoue, B. Alhafni, N. Baimukan, H. Bouamor, N. Habash, [The interplay of variant, size, and task type in arabic pre-trained language models](https://md.research.elamur.ai/free/en/papers/inoue-2021-interplay-variant-size-task-type/), in: Proceedings of the sixth Arabic natural language processing workshop, 2021, pp. 92–104.
12. M. Abdul-Mageed, A. Elmadany, E. M. B. Nagoudi, [Arbert & marbert: Deep bidirectional transformers for arabic](https://md.research.elamur.ai/free/en/papers/abdul-mageed-2021-arbert-marbert-deep-bidirectional-transformers/), arXiv (2020). URL http://arxiv.org/abs/2101.01785 [↗](https://arxiv.org/abs/2101.01785)
13. J. Devlin, M. Chang, K. Lee, K. Toutanova, [BERT: pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/), CoRR abs/1810.04805 (2018). arXiv:1810.04805. URL http://arxiv.org/abs/1810.04805 [↗](https://arxiv.org/abs/1810.04805)
14. V. Sanh, L. Debut, J. Chaumond, T. Wolf, Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter, arXiv preprint arXiv:1910.01108 (2019). [↗](https://arxiv.org/abs/1910.01108)
15. A. Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzmán, E. Grave, M. Ott, L. Zettlemoyer, V. Stoyanov, Unsupervised cross-lingual representation learning at scale, in: Proceedings of the 58th annual meeting of the association for computational linguistics, 2020, pp. 8440–8451. [find](https://scholar.google.com/scholar?q=A%2E+Conneau%2C+K%2E+Khandelwal%2C+N%2E+Goyal%2C+V%2E+Chaudhary%2C+G%2E+Wenzek%2C+F%2E+Guzm%C3%A1n%2C+E%2E+Grave%2C+M%2E+Ott%2C+L%2E+Zettlemoyer%2C+V%2E+Stoyanov%2C+Unsupervised+cross%2Dlingual+representation+learning+at+scale%2C+in%3A+Proceedings+of+)
16. H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozière, N. Goyal, E. Hambro, F. Azhar, et al., [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/), arXiv preprint arXiv:2302.13971 (2023). [↗](https://arxiv.org/abs/2302.13971)
17. Q. Team, Qwen2.5: A party of foundation models (September 2024). URL [https://qwenlm.github.io/blog/qwen2.5/](https://qwenlm.github.io/blog/qwen2.5/) [↗](https://qwenlm.github.io/blog/qwen2.5/)
18. N. Sengupta, S. K. Sahu, B. Jia, S. Katipomu, H. Li, F. Koto, W. Marshall, G. Gosal, C. Liu, Z. Chen, et al., [Jais and jais-chat: Arabic-centric foundation and instruction-tuned open generative large language models](https://md.research.elamur.ai/free/en/papers/sengupta-2023-jais-jais-chat-arabic-centric/), arXiv preprint arXiv:2308.16149 (2023). [↗](https://arxiv.org/abs/2308.16149)

*Updated 31 October 2026*