Challenges / mcit
Arabic Dialect Sentiment Challenge 2025
CompletedStatisticsMetric: Macro-F1mcMCIT
QAR 250,000 + fast-track to marketplace
Deadline 2025-10-31 47 participants
Build a sentiment classifier for Qatari and Gulf Arabic social-media posts about government services, robust to code-switching and dialectal spelling variation. The winning model was hardened through the RAI pipeline and published as citizen-feedback-classifier, now serving MCIT's national feedback programme.
Winning model published to the marketplace
Sadeem AI's Citizen Feedback Classifier passed the RAI pipeline and is live in the catalog.
Leaderboard
Scored on Macro-F1| Rank | Team | Organisation | Macro-F1 | Submissions |
|---|---|---|---|---|
| 1 | Sadeem AI | Sadeem AI | 0.912 | 34 |
| 2 | QCRI ArabicNLP | HBKU | 0.897 | 41 |
| 3 | Falak Analytics | Falak Analytics | 0.884 | 22 |
| 4 | HBKU DialectLab | HBKU | 0.879 | 29 |
| 5 | @fatima_alkhulaifi | independent | 0.871 | 18 |
| 6 | Wahaj Labs | Wahaj Labs | 0.863 | 15 |
| 7 | @arjun_nlp | independent | 0.858 | 26 |
| 8 | HBKU MSc Cohort A | HBKU | 0.842 | 12 |
| 9 | @moza_codes | independent | 0.831 | 9 |
| 10 | @tariq_hassan_ml | independent | 0.815 | 7 |
Submit an entry
Submission upload disabled
This challenge has concluded
Challenge closed
Teams must be registered on the platform. Submissions are evaluated on a held-out national test set and logged to the audit trail.