Get ready for SemEval Emotion Detection [task-11], comprising new datasets for 33 languages, including Hindi and Marathi !! 🤓

Check out our #NLProc Text Based Emotion Analysis (SemEval 2025 Task) shared task. We'll release new datasets in 33 lgges including MSA and Algerian Arabic. CodaBench: codabench.org/competitions/3… Algerian Arabic text snippets come from my translation of Mohammed Dib's trilogy. (To be made public :-) )

Join our SemEval 2025 Task 11: Text-Based Emotion Detection in diverse languages. Task page: github.com/emotion-analys…

Check out Text Based Emotion Analysis (SemEval 2025 Task) SemEval multi/cross-lingual emotion classification shared task in 30+ languages It's a single text classification with a low entry barrier, yet challenging due to many underrepresented languages (Including🇮🇩langs!) codabench.org/competitions/3…

📢 Join to test your emotion classification models in 30+ languages (including 🇷🇴)

Check out our SemEval shared task on perceived emotion in #NLProc github.com/emotion-analys… We released various datasets as well as resources for newcomers and students such lexicons and a blogpost on how to write a system description paper github.com/nedjmaou/Writi… 1/

Check out our shared task on text-based emotion analysis in #NLProc. We're building >30 datasets in many low-resource languages (curated and annotated by native speakers) and it's junior friendly: we'll have a Q&A mentorship session and a writing tutorial in the coming months.

The evaluation period of our Text Based Emotion Analysis (SemEval 2025 Task) SemEval shared task starts tomorrow! We have >30 new datasets including Algerian Arabic. (Dz Ar data is my translation of "La grande maison" by Mohammed Dib en.wikipedia.org/wiki/La_Grande…). Check out github.com/emotion-analys… for more details.

We have >600 participants registered on CodaBench! 😀 The eval phase is still ongoing, you can still join the competition and test you models on >30 languages (high-, mid- and low-resource). We'll have a paper writing tutorial in Feb if you're new to #NLProc.

BRIGHTER: a new data collection for emotion in #NLProc. New multi-labeled datasets in 28 languages from 7 distinct families, collected and annotated by native speakers, accepted at #ACL2025NLP (main). 📄Preprint arxiv.org/abs/2502.11926 A massive team effort! 1/

Co-led w\ Shamsuddeen Hassan Muhammad, PhD and Saif M. Mohammad Thanks to the great team members including Jan Philip Wahle terryruas Nirmal Surange Meriem Beloucif Christine de Kock Daniela Teodorescu and many others! Part of our Text Based Emotion Analysis (SemEval 2025 Task) SemEval task (Task paper: arxiv.org/abs/2503.07269) 2/2

BRIGHTER: multi-labeled datasets in 28 languages from 7 distinct families for emotion in #NLProc collected and annotated by native speakers to be presented today at #ACL2025 Session 9: IP-Orals – Resources and Evaluation 2 pm Hall B.

Our ✨BRIGHTER✨ paper won the a best resource paper award at ACL 2025 #ACL2025! Big thanks to all the team members!

And our SemEval task won a best task description award 🥳 Co-led with Shamsuddeen Hassan Muhammad, PhD and Saif M. Mohammad. Thanks to all the team members!

Congratulations to the best task awards! Winner: SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection Runner Up: SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes #ACL2025NLP