Elamur Research⌕
☰
home / papers / 2026 / JobArabi: An Arabic Corpus and Analysis of Job Announcements from Social Media

JobArabi: An Arabic Corpus and Analysis of Job Announcements from Social Media

Summary

Arabic NLP lacks large, domain-specific resources on recruitment language, even though social media has become a major hiring channel across the MENA region. The authors build JobArabi, a corpus of 20,528 public X posts and replies about jobs, gathered through the Meltwater monitoring platform between January 2024 and October 2025. Rather than translating English hiring terms, they designed a 21-keyword Arabic query covering:

  • formal and colloquial registers
  • synonyms and common collocations
  • singular and plural forms
  • masculine and feminine job wording
  • urgency markers

Metadata such as timestamps, engagement figures and, where available, location support temporal and regional study. The analysis shows rapid growth in recruitment posting and a strong Gulf concentration. Gender-specific hiring wording remains common. Replies often voice frustration, anger and sadness about opaque or non-inclusive practices. The resource supports information extraction, trend tracking and bias auditing for Arabic job ads, as well as social-science research on Arab labor markets. Caveats include platform bias, text-only processing and inconsistent data access between the two years.

Key points

  • Corpus size and split: 20,528 mentions from X, with 8,316 from 2024 (full year) and 12,212 from 1 January to 20 October 2025. The 2025 portion exceeded the 2024 total by 46.8% in about ten months.
  • Query design: The 21-keyword query targets five linguistic dimensions: formality, synonymy/collocations, pluralization, gender inflection and immediacy. For example, it includes separate phrases for a wanted male employee and a wanted female employee.
  • Geographic skew: 71.21% of geo-tagged posts come from Saudi Arabia. The corpus is best read as a Gulf/GCC-centred view rather than a picture of the whole MENA market.
  • Known limitations:
    • Keyword-based collection misses English code-switched or implicit job ads.
    • Including replies mixes actual postings with user reactions.
    • Image-based ads are not processed with OCR.
    • 2024 data are raw posts, while 2025 data come from aggregated dashboard analytics.
  • Release and licensing: Access is on request for vetted, non-commercial research under CC BY-NC-SA 4.0. User identifiers are removed or anonymized, and scripts are planned for GitHub. The work was funded by QNRF grant NPRP14C-0916-210015.

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

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/59fr3tst4j4z

@inproceedings{zaghouani2026jobarabi,
  title = {{JobArabi: An Arabic Corpus and Analysis of Job Announcements from Social Media}},
  author = {Zaghouani, Wajdi and Ibrahim, Shimaa Amer and Bessghaier, Mabrouka and Bouamor, Houda},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/59fr3tst4j4z},
  url = {https://doi.org/10.63317/59fr3tst4j4z}
}

References

30 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Yousef Altaher, Ali Fadel, Mazen Alotaibi, Mazen Alyazidi, Mishari Al-Mutairi, Mutlaq Aldhbuiub, Abdulrahman Mosaibah, Abdelrahman Rezk, Abdulrazzaq Alhendi, Mazen Abo Shal, Emad A. Alghamdi, Maged S. Alshaibani, Jezia Zakraoui, Wafaa Mohammed, Kamel Gaanoun, Khalid N. Elmadani, Mustafa Ghaleb, Nouamane Tazi, Raed Alharbi, Maraim Masoud, and Zaid Alyafeai. 2022. Masader plus: A new interface for exploring +500 arabic nlp datasets. ↗
  2. Zaid Alyafeai, Maraim Masoud, Mustafa Ghaleb, and Maged S. Al-shaibani. 2022. Masader: Metadata sourcing for Arabic text and speech data resources. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 6340–6351, Marseille, France. European Language Resources Association. find
  3. Md Rafiul Biswas, Shimaa Ibrahim, Mabrouka Bessghaier, and Wajdi Zaghouani. 2025. Evaluation of pretrained and instruction-based pre-trained models for emotion detection in arabic social media text. In Proceedings of the 15th International Conference on Recent Advances in Natural Language Processing-Natural Language Processing in the Generative AI Era, pages 158–165. find
  4. Axel Bruns and Jean Burgess. 2011. The use of twitter hashtags in the formation of ad hoc publics. In Proceedings of the 6th European Consortium for Political Research General Conference. find
  5. Emily D Campion and Michael A Campion. 2020. Using computer-assisted text analysis (cata) to inform employment decisions: Approaches, software, and findings. Research in personnel and human resources management, pages 285–325. ↗
  6. Anis Charfi, Andria Atalla, Raghda Akasheh, Mabrouka Bessghaier, and Wajdi Zaghouani. 2024a. A web-based hate speech detection system for dialectal arabic. In DATA, pages 478– 485. find
  7. Anis Charfi, Mabrouka Ben-Sghaier, Andria Samy Raouf Atalla, Raghda Akasheh, Sara Al-Emadi, and Wajdi Zaghouani. 2024b. Marasta: A multi-dialectal arabic cross-domain stance corpus. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11060–11069. find
  8. Anis Charfi, Mabrouka Besghaier, Raghda Akasheh, Andria Atalla, and Wajdi Zaghouani. 2024c. Hate speech detection with adhar: a multi-dialectal hate speech corpus in arabic. Frontiers in Artificial Intelligence, 7:1391472. ↗
  9. Anis Charfi, Syed Hassan Mehdi, Esraa Mohamed, and Mabrouka Bessghaier. 2024d. Arap-irony: A multi-dialectal arabic irony corpus for irony detection. In International Conference on Arabic Language Processing, pages 218–229. Springer. find
  10. Mo El-Haj. 2025. Arabjobs: A multinational corpus of arabic job ads. ↗
  11. AbdelRahim A. Elmadany, Hamdy Mubarak, and Walid Magdy. 2018. Arsas: An arabic speech-act and sentiment corpus of tweets. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018) — OSACT 3 Workshop, Miyazaki, Japan. European Language Resources Association (ELRA). find
  12. Lauren Friedman, Hubert Jin, Song Chen, Gary Krug, and Stephanie Strassel. 2012. GALE phase 2 arabic broadcast news parallel text. Web Download. LDC2012T18; ISBN 1-58563-626-6; ISLRN 198-319-621-200-1. ↗
  13. Danielle Gaucher, Justin Friesen, and Aaron C. Kay. 2011. Evidence that gendered wording in job advertisements exists and sustains gender inequality. Journal of Personality and Social Psychology, 101(1):109–128. ↗
  14. Philip N. Howard, Aidan Duffy, Deen Freelon, Muzammil M. Hussain, Will Mari, and Marwa Mazaid. 2011. Opening closed regimes: What was the role of social media during the arab spring? International Journal of Communication, 5:18. find
  15. Simon Kemp and DataReportal. 2025a. Digital 2025: Global overview report. https://datareportal.com/reports/digital-Ac-2025-global-overview-report. cessed Oct. 2025. ↗
  16. Simon Kemp and DataReportal. 2025b. https: Digital 2025: Saudi arabia. //datareportal.com/reports/digital-2025-saudi-arabia. Headline social media penetration figures for MENA exemplar; accessed Oct. 2025. find
  17. Jieun Lee, Vladimir Hlasny, et al. 2023. Social capital and workers’ job prospects in the mena region. Sociologickỳ časopis/Czech Sociological Review, 58(6):637–670. ↗
  18. Pierre Lison and Jörg Tiedemann. 2016. Open-Subtitles2016: Extracting large parallel corpora from movie and TV subtitles. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 923–929, Portorož, Slovenia. European Language Resources Association (ELRA). find
  19. Gilad Lotan, Erhardt Graeff, Mike Ananny, Devin Gaffney, Ian Pearce, and danah boyd. 2011. The revolutions were tweeted: Information flows during the 2011 tunisian and egyptian revolutions. International Journal of Communication, 5:1375–1405. find
  20. Ines Mergel. 2013. A framework for interpreting social media interactions in the public sector. Government Information Quarterly, 30(4):327–334. ↗
  21. Hamdy Mubarak, Kareem Darwish, and Walid Magdy. 2017. Abusive language detection on Arabic social media. In Proceedings of the First Workshop on Abusive Language Online, pages 52–56, Vancouver, BC, Canada. Association for Computational Linguistics. find
  22. Mahmoud Nabil, Mohamed Aly, and Amir Atiya. 2015. ASTD: Arabic sentiment tweets dataset. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 2515–2519, Lisbon, Portugal. Association for Computational Linguistics. ↗
  23. Elena Senger, Mike Zhang, Rob van der Goot, and Barbara Plank. 2024. Deep learning-based computational job market analysis: A survey on skill extraction and classification from job postings. In Proceedings of the First Workshop on Natural Language Processing for Human Resources (NLP4HR 2024), pages 1–15, St. Julian’s, Malta. Association for Computational Linguistics. find
  24. Cath Sleeman and Nesta team. 2021. The open jobs observatory. https://www.nesta.org.uk/project/open-jobs-observatory/. Accessed Oct. 2025. ↗
  25. Mariagrazia Squicciarini and Heike Nachtigall. 2021a. Demand for ai skills in jobs: Evidence from online job postings. Technical Report 2021/03, OECD Science, Technology and Industry Working Papers. ↗
  26. Mariagrazia Squicciarini and Heike Nachtigall. 2021b. Demand for ai skills in jobs: Evidence from online job postings. OECD Science, Technology and Industry Working Papers, 2021(3):1– 74. ↗
  27. Gurpal S Sran. 2025. Disclosing labor demand: Evidence from online job postings. The Accounting Review, 100(5):345–374. ↗
  28. Zeynep Tufekci. 2017. Twitter and Tear Gas: The Power and Fragility of Networked Protest. Yale University Press, New Haven, CT. ↗
  29. Amit Verma, Phillip Frank, and Kamal Lamsal. 2021. An exploratory study of skill requirements for social media positions: A content analysis of job advertisements. arXiv preprint arXiv:2106.11040. ↗
  30. Wajdi Zaghouani and Anis Charfi. 2018. Arap-tweet: A large multi-dialect twitter corpus for gender, age and language variety identification. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zaghouani-2026-jobarabi-arabic-corpus-analysis-job/