Participants were required to predict the presence or absence of each perceived emotion, but without using any training data in the target language. Instead, they were permitted to use labeled dataset(s) from at least one other language. For instance, one could use German data for training when testing on English. This track focuses on cross-lingual transfer and explores how data from various languages can support emotion detection in low-resource settings, as well as the ability of models to generalise across domains.
Publication
Shamsuddeen Hassan Muhammad, Nedjma Ousidhoum, Idris Abdulmumin, Seid Muhie Yimam, Jan Philip Wahle, Terry Lima Ruas, Meriem Beloucif, Christine De Kock, Tadesse Destaw Belay, Ibrahim Said Ahmad, Nirmal Surange, Daniela Teodorescu, David Ifeoluwa Adelani, Alham Fikri Aji, Felermino Dario Mario Ali, Vladimir Araujo, Abinew Ali Ayele, Oana Ignat, Alexander Panchenko, Yi Zhou, and Saif Mohammad. 2025. SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection. In Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025), pages 2558–2569, Vienna, Austria. Association for Computational Linguistics.
Language
Spanish
English
NLP topic
Dataset
Year
2025
Publication link
Task results
| System | MacroF1 Sort ascending |
|---|---|
| deepwave | 0.8310 |
| maomao | 0.8060 |
