Name: mteb/EmotionAnalysis
Creator: mteb
Published: 2026-04-19 14:01:54
License: 暂无描述

下载链接：

https://hf-mirror.com/datasets/mteb/EmotionAnalysis

下载链接

链接失效反馈

官方服务：

资源简介：

--- annotations_creators: - human-annotated language: - afr - amh - arq - ary - cdo - deu - eng - gaz - hau - hin - ibo - ind - jav - kin - mar - pcm - ron - rus - som - spa - sun - swa - swe - tat - tir - ukr - vmw - xho - yor - zul license: cc-by-4.0 multilinguality: multilingual source_datasets: - llama-lang-adapt/EmotionAnalysisFinal task_categories: - text-classification task_ids: - sentiment-classification dataset_info: - config_name: afr features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 108045.0 num_examples: 1065 - name: train num_bytes: 10095.0 num_examples: 98 download_size: 78096 dataset_size: 118140.0 - config_name: amh features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 469331.2807215333 num_examples: 1772 - name: train num_bytes: 159424.0 num_examples: 592 download_size: 341676 dataset_size: 628755.2807215333 - config_name: arq features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 144068.1019955654 num_examples: 901 - name: train num_bytes: 16253.0 num_examples: 100 download_size: 81131 dataset_size: 160321.1019955654 - config_name: ary features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 116400.35467980296 num_examples: 809 - name: train num_bytes: 37747.0 num_examples: 267 download_size: 94836 dataset_size: 154147.35467980296 - config_name: chn features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 16913.339894019682 num_examples: 92 - name: train num_bytes: 883.725 num_examples: 5 download_size: 16739 dataset_size: 17797.06489401968 - config_name: deu features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 636845.2258064516 num_examples: 2598 - name: train num_bytes: 48760.0 num_examples: 200 download_size: 447925 dataset_size: 685605.2258064516 - config_name: eng features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 275236.7705095772 num_examples: 2754 - name: train num_bytes: 11081.637931034482 num_examples: 115 download_size: 174757 dataset_size: 286318.4084406117 - config_name: esp features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 117654.0 num_examples: 1695 - name: train num_bytes: 14366.0 num_examples: 184 download_size: 83426 dataset_size: 132020.0 - config_name: gaz features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 279017.94770482276 num_examples: 1691 - name: train num_bytes: 97310.73519163764 num_examples: 571 download_size: 254657 dataset_size: 376328.6828964604 - config_name: hau features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 102892.0 num_examples: 1080 - name: train num_bytes: 34146.0 num_examples: 356 download_size: 91729 dataset_size: 137038.0 - config_name: hin features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 217653.0 num_examples: 1010 - name: train num_bytes: 21462.0 num_examples: 100 download_size: 106776 dataset_size: 239115.0 - config_name: ibo features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 115990.25831024931 num_examples: 1411 - name: train num_bytes: 39216.95615866388 num_examples: 478 download_size: 88887 dataset_size: 155207.21446891318 - config_name: ind features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 87773.0 num_examples: 851 - name: train num_bytes: 15285.0 num_examples: 156 download_size: 67219 dataset_size: 103058.0 - config_name: jav features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 93396.0 num_examples: 837 - name: train num_bytes: 16121.0 num_examples: 151 download_size: 73615 dataset_size: 109517.0 - config_name: kin features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 183324.3476848091 num_examples: 1226 - name: train num_bytes: 61004.74201474201 num_examples: 405 download_size: 160281 dataset_size: 244329.0896995511 - config_name: mar features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 234673.0 num_examples: 1000 - name: train num_bytes: 21003.0 num_examples: 100 download_size: 105651 dataset_size: 255676.0 - config_name: pcm features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 245948.0 num_examples: 1870 - name: train num_bytes: 85256.0 num_examples: 620 download_size: 207816 dataset_size: 331204.0 - config_name: ron features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 140555.2797140304 num_examples: 1118 - name: train num_bytes: 15305.0 num_examples: 123 download_size: 103058 dataset_size: 155860.2797140304 - config_name: rus features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 118911.002 num_examples: 947 - name: train num_bytes: 22367.48743718593 num_examples: 190 download_size: 85267 dataset_size: 141278.48943718593 - config_name: som features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 289372.23172169813 num_examples: 1693 - name: train num_bytes: 95307.8445229682 num_examples: 560 download_size: 261147 dataset_size: 384680.07624466636 - config_name: sun features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 88659.0 num_examples: 926 - name: train num_bytes: 19124.0 num_examples: 199 download_size: 70761 dataset_size: 107783.0 - config_name: swe features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 239988.18686868687 num_examples: 1149 - name: train num_bytes: 38948.365 num_examples: 193 download_size: 182457 dataset_size: 278936.55186868686 - config_name: swh features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 153837.1497584541 num_examples: 1640 - name: train num_bytes: 51577.10526315789 num_examples: 549 download_size: 145852 dataset_size: 205414.25502161199 - config_name: tat features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 118466.28 num_examples: 958 - name: train num_bytes: 23679.825 num_examples: 195 download_size: 85339 dataset_size: 142146.105 - config_name: tir features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 467038.79673913046 num_examples: 1838 - name: train num_bytes: 159966.0 num_examples: 614 download_size: 348855 dataset_size: 627004.7967391305 - config_name: ukr features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 259638.72649955237 num_examples: 2233 - name: train num_bytes: 29586.0 num_examples: 249 download_size: 170714 dataset_size: 289224.7264995524 - config_name: vmw features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 73160.0 num_examples: 777 - name: train num_bytes: 23938.0 num_examples: 258 download_size: 66824 dataset_size: 97098.0 - config_name: xho features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 104948.0 num_examples: 1594 - name: train num_bytes: 44368.0 num_examples: 682 download_size: 95386 dataset_size: 149316.0 - config_name: yor features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 170003.0 num_examples: 1500 - name: train num_bytes: 54902.0 num_examples: 497 download_size: 144492 dataset_size: 224905.0 - config_name: zul features: - name: text dtype: string - name: label sequence: int64 splits: - name: validation num_bytes: 0 num_examples: 0 - name: test num_bytes: 135132.3106985833 num_examples: 2040 - name: train num_bytes: 58290.45942857143 num_examples: 873 download_size: 136624 dataset_size: 193422.7701271547 configs: - config_name: afr data_files: - split: validation path: afr/validation-* - split: test path: afr/test-* - split: train path: afr/train-* - config_name: amh data_files: - split: validation path: amh/validation-* - split: test path: amh/test-* - split: train path: amh/train-* - config_name: arq data_files: - split: validation path: arq/validation-* - split: test path: arq/test-* - split: train path: arq/train-* - config_name: ary data_files: - split: validation path: ary/validation-* - split: test path: ary/test-* - split: train path: ary/train-* - config_name: chn data_files: - split: validation path: chn/validation-* - split: test path: chn/test-* - split: train path: chn/train-* - config_name: deu data_files: - split: validation path: deu/validation-* - split: test path: deu/test-* - split: train path: deu/train-* - config_name: eng data_files: - split: validation path: eng/validation-* - split: test path: eng/test-* - split: train path: eng/train-* - config_name: esp data_files: - split: validation path: esp/validation-* - split: test path: esp/test-* - split: train path: esp/train-* - config_name: gaz data_files: - split: validation path: gaz/validation-* - split: test path: gaz/test-* - split: train path: gaz/train-* - config_name: hau data_files: - split: validation path: hau/validation-* - split: test path: hau/test-* - split: train path: hau/train-* - config_name: hin data_files: - split: validation path: hin/validation-* - split: test path: hin/test-* - split: train path: hin/train-* - config_name: ibo data_files: - split: validation path: ibo/validation-* - split: test path: ibo/test-* - split: train path: ibo/train-* - config_name: ind data_files: - split: validation path: ind/validation-* - split: test path: ind/test-* - split: train path: ind/train-* - config_name: jav data_files: - split: validation path: jav/validation-* - split: test path: jav/test-* - split: train path: jav/train-* - config_name: kin data_files: - split: validation path: kin/validation-* - split: test path: kin/test-* - split: train path: kin/train-* - config_name: mar data_files: - split: validation path: mar/validation-* - split: test path: mar/test-* - split: train path: mar/train-* - config_name: pcm data_files: - split: validation path: pcm/validation-* - split: test path: pcm/test-* - split: train path: pcm/train-* - config_name: ron data_files: - split: validation path: ron/validation-* - split: test path: ron/test-* - split: train path: ron/train-* - config_name: rus data_files: - split: validation path: rus/validation-* - split: test path: rus/test-* - split: train path: rus/train-* - config_name: som data_files: - split: validation path: som/validation-* - split: test path: som/test-* - split: train path: som/train-* - config_name: sun data_files: - split: validation path: sun/validation-* - split: test path: sun/test-* - split: train path: sun/train-* - config_name: swe data_files: - split: validation path: swe/validation-* - split: test path: swe/test-* - split: train path: swe/train-* - config_name: swh data_files: - split: validation path: swh/validation-* - split: test path: swh/test-* - split: train path: swh/train-* - config_name: tat data_files: - split: validation path: tat/validation-* - split: test path: tat/test-* - split: train path: tat/train-* - config_name: tir data_files: - split: validation path: tir/validation-* - split: test path: tir/test-* - split: train path: tir/train-* - config_name: ukr data_files: - split: validation path: ukr/validation-* - split: test path: ukr/test-* - split: train path: ukr/train-* - config_name: vmw data_files: - split: validation path: vmw/validation-* - split: test path: vmw/test-* - split: train path: vmw/train-* - config_name: xho data_files: - split: validation path: xho/validation-* - split: test path: xho/test-* - split: train path: xho/train-* - config_name: yor data_files: - split: validation path: yor/validation-* - split: test path: yor/test-* - split: train path: yor/train-* - config_name: zul data_files: - split: validation path: zul/validation-* - split: test path: zul/test-* - split: train path: zul/train-* tags: - mteb - text ---  <div align="center" style="padding: 40px 20px; background-color: white; border-radius: 12px; box-shadow: 0 2px 10px rgba(0, 0, 0, 0.05); max-width: 600px; margin: 0 auto;"> <h1 style="font-size: 3.5rem; color: #1a1a1a; margin: 0 0 20px 0; letter-spacing: 2px; font-weight: 700;">EmotionAnalysisPlus</h1> <div style="font-size: 1.5rem; color: #4a4a4a; margin-bottom: 5px; font-weight: 300;">An <a href="https://github.com/embeddings-benchmark/mteb" style="color: #2c5282; font-weight: 600; text-decoration: none;" onmouseover="this.style.textDecoration='underline'" onmouseout="this.style.textDecoration='none'">MTEB</a> dataset</div> <div style="font-size: 0.9rem; color: #2c5282; margin-top: 10px;">Massive Text Embedding Benchmark</div> </div> Multi-label emotion classification dataset for 28 languages released with the BRIGHTER project and SemEval-2025 Task 11. | | | |---------------|---------------------------------------------| | Task category | t2c | | Domains | Social, Written | | Reference | https://github.com/emotion-analysis-project/SemEval2025-Task11 | Source datasets: - [llama-lang-adapt/EmotionAnalysisFinal](https://huggingface.co/datasets/llama-lang-adapt/EmotionAnalysisFinal) ## Dataset Preparation in MTEB This repository is a staging copy of `llama-lang-adapt/EmotionAnalysisFinal` for MTEB. The intended long-term canonical benchmark copy is `mteb/EmotionAnalysis`. ### Transformations - Converted per-emotion indicator columns into the MTEB multi-label format: `label: list[int]` - Preserved the task-facing subset names, including `gaz` and `swh`, while sourcing from the original Hub configs - Backfilled a `train` split where missing for benchmark compatibility before cleaning - Applied dataset cleaning before upload to reduce duplicates and copied-train overlap in the staging copy ### Label Schema - `0`: anger - `1`: disgust - `2`: fear - `3`: joy - `4`: sadness - `5`: surprise ### Splits and subsets - Language-specific configs from the benchmark task are preserved - The staged copy includes the cleaned train/validation/test-style splits used by `EmotionAnalysisPlus` ## How to evaluate on this task You can evaluate an embedding model on this dataset using the following code: ```python import mteb task = mteb.get_task("EmotionAnalysisPlus") evaluator = mteb.MTEB([task]) model = mteb.get_model(YOUR_MODEL) evaluator.run(model) ```  To learn more about how to run models on `mteb` task check out the [GitHub repository](https://github.com/embeddings-benchmark/mteb). ## Citation If you use this dataset, please cite the dataset as well as [mteb](https://github.com/embeddings-benchmark/mteb), as this dataset likely includes additional processing as a part of the [MMTEB Contribution](https://github.com/embeddings-benchmark/mteb/tree/main/docs/mmteb). ```bibtex @article{enevoldsen2025mmtebmassivemultilingualtext, title={MMTEB: Massive Multilingual Text Embedding Benchmark}, author={Kenneth Enevoldsen and Isaac Chung and Imene Kerboua and Márton Kardos and Ashwin Mathur and David Stap and Jay Gala and Wissam Siblini and Dominik Krzemiński and Genta Indra Winata and Saba Sturua and Saiteja Utpala and Mathieu Ciancone and Marion Schaeffer and Gabriel Sequeira and Diganta Misra and Shreeya Dhakal and Jonathan Rystrøm and Roman Solomatin and Ömer Çağatan and Akash Kundu and Martin Bernstorff and Shitao Xiao and Akshita Sukhlecha and Bhavish Pahwa and Rafał Poświata and Kranthi Kiran GV and Shawon Ashraf and Daniel Auras and Björn Plüster and Jan Philipp Harries and Loïc Magne and Isabelle Mohr and Mariya Hendriksen and Dawei Zhu and Hippolyte Gisserot-Boukhlef and Tom Aarsen and Jan Kostkan and Konrad Wojtasik and Taemin Lee and Marek Šuppa and Crystina Zhang and Roberta Rocca and Mohammed Hamdy and Andrianos Michail and John Yang and Manuel Faysse and Aleksei Vatolin and Nandan Thakur and Manan Dey and Dipam Vasani and Pranjal Chitale and Simone Tedeschi and Nguyen Tai and Artem Snegirev and Michael Günther and Mengzhou Xia and Weijia Shi and Xing Han Lù and Jordan Clive and Gayatri Krishnakumar and Anna Maksimova and Silvan Wehrli and Maria Tikhonova and Henil Panchal and Aleksandr Abramov and Malte Ostendorff and Zheng Liu and Simon Clematide and Lester James Miranda and Alena Fenogenova and Guangyu Song and Ruqiya Bin Safi and Wen-Ding Li and Alessia Borghini and Federico Cassano and Hongjin Su and Jimmy Lin and Howard Yen and Lasse Hansen and Sara Hooker and Chenghao Xiao and Vaibhav Adlakha and Orion Weller and Siva Reddy and Niklas Muennighoff}, publisher = {arXiv}, journal={arXiv preprint arXiv:2502.13595}, year={2025}, url={https://arxiv.org/abs/2502.13595}, doi = {10.48550/arXiv.2502.13595}, } @article{muennighoff2022mteb, author = {Muennighoff, Niklas and Tazi, Nouamane and Magne, Loïc and Reimers, Nils}, title = {MTEB: Massive Text Embedding Benchmark}, publisher = {arXiv}, journal={arXiv preprint arXiv:2210.07316}, year = {2022} url = {https://arxiv.org/abs/2210.07316}, doi = {10.48550/ARXIV.2210.07316}, } ``` # Dataset Statistics <details> <summary> Dataset Statistics</summary> The following code contains the descriptive statistics from the task. These can also be obtained using: ```python import mteb task = mteb.get_task("EmotionAnalysisPlus") desc_stats = task.metadata.descriptive_stats ``` ```json { "validation": { "num_samples": 9913, "number_texts_intersect_with_train": 9912, "text_statistics": { "total_text_length": 913579, "min_text_length": 6, "average_text_length": 92.15968929688287, "max_text_length": 2022, "unique_texts": 9912 }, "image_statistics": null, "audio_statistics": null, "label_statistics": { "min_labels_per_text": 0, "average_label_per_text": 0.9135478664380107, "max_labels_per_text": 5, "unique_labels": 7, "labels": { "3": { "count": 1956 }, "None": { "count": 2679 }, "2": { "count": 721 }, "0": { "count": 1509 }, "1": { "count": 1584 }, "4": { "count": 2091 }, "5": { "count": 1195 } } } }, "test": { "num_samples": 43882, "number_texts_intersect_with_train": 17, "text_statistics": { "total_text_length": 4126105, "min_text_length": 3, "average_text_length": 94.02727769928444, "max_text_length": 3779, "unique_texts": 43848 }, "image_statistics": null, "audio_statistics": null, "label_statistics": { "min_labels_per_text": 0, "average_label_per_text": 1.0114169819060206, "max_labels_per_text": 6, "unique_labels": 7, "labels": { "3": { "count": 9680 }, "None": { "count": 10566 }, "4": { "count": 9202 }, "2": { "count": 4844 }, "0": { "count": 7680 }, "1": { "count": 6957 }, "5": { "count": 6020 } } } }, "train": { "num_samples": 9913, "number_texts_intersect_with_train": null, "text_statistics": { "total_text_length": 913579, "min_text_length": 6, "average_text_length": 92.15968929688287, "max_text_length": 2022, "unique_texts": 9912 }, "image_statistics": null, "audio_statistics": null, "label_statistics": { "min_labels_per_text": 0, "average_label_per_text": 0.9135478664380107, "max_labels_per_text": 5, "unique_labels": 7, "labels": { "3": { "count": 1956 }, "None": { "count": 2679 }, "2": { "count": 721 }, "0": { "count": 1509 }, "1": { "count": 1584 }, "4": { "count": 2091 }, "5": { "count": 1195 } } } } } ``` </details> --- *This dataset card was automatically generated using [MTEB](https://github.com/embeddings-benchmark/mteb)*

应用场景：