MY ALT TEXT
Languages Covered in the BRIGHTER Dataset
Afrikaans (afr), Algerian Arabic (arq), Amharic (amh), Portuguese (Brazilian) (ptbr), Mandarin Chinese (chn), Emakhuwa (vmw), English (eng), German (deu), Hausa (hau), Hindi (hin), Igbo (ibo), Indonesian (ind), isiXhosa (xho), isiZulu (zul), Javanese (jav), Kinyarwanda (kin), Spanish (Latin American) (esp), Marathi (mar), Moroccan Arabic (ary), Portuguese (Mozambican) (pt-MZ), Nigerian-Pidgin (pcm), Oromo (orm), Romanian (ron), Russian (rus), Somali (som), Sundanese (sun), Swahili (swa), Swedish (swe), Tatar (tat), Tigrinya (tir), Ukrainian (ukr), Yoruba (yor).

TL;DR

We introduce BRIGHTER: a new emotion recognition dataset collection in 28 languages that originate from 7 distinct language families. Many of these languages are considered low-resource, and are mainly spoken in regions characterised by a limited availability of NLP resources (e.g., Africa, Asia, Latin America).

Our contribuitions:

  • A linguistically diverse multilingual dataset: BRIGHTER consists of nearly 100k emotion-annotated instances in 28 languages, predominantly from Africa, Asia, Eastern Europe, and Latin America. The dataset spans 7 language families and covers a variety of domains, including social media, speeches, news, literature, and reviews. Each instance is multi-labeled with six emotion classes — joy, sadness, anger, fear, surprise, disgust, and neutral — and annotated within four emotion intensity levels, ranging from 0 to 3.
  • Baseline Evaluation: We provide an initial set of monolingual and crosslingual experiments, benchmarking Large Language Models (LLMs) for multi-label emotion identification and intensity prediction. Our results highlight the performance disparities across languages, showing that LLMs struggle with perceived emotions in text, especially for low-resource languages, and often perform better when prompted in English.

Statistics

Below are the statistics of our dataset collection:

MY ALT TEXT
×
Zoomed Image

Experimental Results

Comparing models' performance across languages when prompted in English (orange) vs. when prompted in the target language (blue). LLMs perform better when prompted in English.

MY ALT TEXT

Performance of different LLMs across three prompt paraphrases on the English test set. Different prompts impact model performance.

MY ALT TEXT

BibTeX


@misc{muhammad2025brighterbridginggaphumanannotated,
  title={BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages}, 
  author={Shamsuddeen Hassan Muhammad and Nedjma Ousidhoum and Idris Abdulmumin and Jan Philip Wahle and Terry Ruas and Meriem Beloucif and Christine de Kock and Nirmal Surange and Daniela Teodorescu and Ibrahim Said Ahmad and David Ifeoluwa Adelani and Alham Fikri Aji and Felermino D. M. A. Ali and Ilseyar Alimova and Vladimir Araujo and Nikolay Babakov and Naomi Baes and Ana-Maria Bucur and Andiswa Bukula and Guanqun Cao and Rodrigo Tufino Cardenas and Rendi Chevi and Chiamaka Ijeoma Chukwuneke and Alexandra Ciobotaru and Daryna Dementieva and Murja Sani Gadanya and Robert Geislinger and Bela Gipp and Oumaima Hourrane and Oana Ignat and Falalu Ibrahim Lawan and Rooweither Mabuya and Rahmad Mahendra and Vukosi Marivate and Andrew Piper and Alexander Panchenko and Charles Henrique Porto Ferreira and Vitaly Protasov and Samuel Rutunda and Manish Shrivastava and Aura Cristina Udrea and Lilian Diana Awuor Wanzare and Sophie Wu and Florian Valentin Wunderlich and Hanif Muhammad Zhafran and Tianhui Zhang and Yi Zhou and Saif M. Mohammad},
  year={2025},
  eprint={2502.11926},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2502.11926}
}

@inproceedings{muhammad-etal-2025-semeval,
  title = "{S}em{E}val Task 11: Bridging the Gap in Text-Based Emotion Detection",
  author = "Muhammad, Shamsuddeen Hassan and Ousidhoum, Nedjma and Abdulmumin, Idris and Yimam, Seid Muhie and Wahle, Jan Philip and Ruas, Terry and Beloucif, Meriem and De Kock, Christine and Belay, Tadesse Destaw and Ahmad, Ibrahim Said and Surange, Nirmal and Teodorescu, Daniela and Adelani, David Ifeoluwa and Aji, Alham Fikri and Ali, Felermino and Araujo, Vladimir and Ayele, Abinew Ali and Ignat, Oana and Panchenko, Alexander and Zhou, Yi and Mohammad, Saif M.",
  booktitle = "Proceedings of the 19th International Workshop on Semantic Evaluation (SemEval-2025)",
  month = july,
  year = "2025",
  address = "Vienna, Austria",
  publisher = "Association for Computational Linguistics",
  url = "",
  doi = "",
  pages = ""
}