datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
ExperimentDATA_knowledge_distillation_vs_fine_tuninghateful_memes_expandedhateful_memes
The Hateful Memes Challenge README
The Hateful Memes Challenge is a dataset and benchmark created by Facebook AI to drive and measure progress on multimodal reasoning and understanding. The task focuses on detecting hate speech in multimodal memes.
Please see the paper for further details:
The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes
D. Kiela, H. Firooz, A. Mohan, V. Goswami, A. Singh, P. Ringshia, D. Testuggine
For more details, see also the website:… See the full description on the dataset page: https://huggingface.co/datasets/neuralcatcher/hateful_memes.korean-hate-speechreference: https://github.com/kocohub/korean-hate-speech
@inproceedings{moon-etal-2020-beep,
title = "{BEEP}! {K}orean Corpus of Online News Comments for Toxic Speech Detection",
author = "Moon, Jihyung and
Cho, Won Ik and
Lee, Junbum",
booktitle = "Proceedings of the Eighth International Workshop on Natural Language Processing for Social Media",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics"… See the full description on the dataset page: https://huggingface.co/datasets/nayohan/korean-hate-speech.hate_speech_offensive
Dataset Card for [Dataset Name]
Dataset Summary
An annotated dataset for hate speech and offensive language detection on tweets.
Supported Tasks and Leaderboards
[More Information Needed]
Languages
English (en)
Dataset Structure
Data Instances
{
"count": 3,
"hate_speech_annotation": 0,
"offensive_language_annotation": 0,
"neither_annotation": 3,
"label": 2, # "neither"
"tweet": "!!! RT @mayasolovely: As a woman you… See the full description on the dataset page: https://huggingface.co/datasets/tdavidson/hate_speech_offensive.measuring-hate-speech
Dataset card for Measuring Hate Speech
This is a public release of the dataset described in Kennedy et al. (2020) and Sachdeva et al. (2022), consisting of 39,565 comments annotated by 7,912 annotators, for 135,556 combined rows. The primary outcome variable is the "hate speech score" but the 10 constituent ordinal labels (sentiment, (dis)respect, insult, humiliation, inferior status, violence, dehumanization, genocide, attack/defense, hate speech benchmark) can also be treated as… See the full description on the dataset page: https://huggingface.co/datasets/ucberkeley-dlab/measuring-hate-speech.kmhas_korean_hate_speechThe K-MHaS (Korean Multi-label Hate Speech) dataset contains 109k utterances from Korean online news comments labeled with 8 fine-grained hate speech classes or Not Hate Speech class.
The fine-grained hate speech classes are politics, origin, physical, age, gender, religion, race, and profanity and these categories are selected in order to reflect the social and historical context.hatexplainHatexplain is the first benchmark hate speech dataset covering multiple aspects of the issue. Each post in the dataset is annotated from three different perspectives: the basic, commonly used 3-class classification (i.e., hate, offensive or normal), the target community (i.e., the community that has been the victim of hate speech/offensive speech in the post), and the rationales, i.e., the portions of the post on which their labelling decision (as hate, offensive or normal) is based.korean-hate-speechHello AI-it!
tweets_hate_speech_detection
Dataset Card for Tweets Hate Speech Detection
Dataset Summary
The objective of this task is to detect hate speech in tweets. For the sake of simplicity, we say a tweet contains hate speech if it has a racist or sexist sentiment associated with it. So, the task is to classify racist or sexist tweets from other tweets.
Formally, given a training sample of tweets and labels, where label ‘1’ denotes the tweet is racist/sexist and label ‘0’ denotes the tweet is not… See the full description on the dataset page: https://huggingface.co/datasets/tweets-hate-speech-detection/tweets_hate_speech_detection.hate_speech18These files contain text extracted from Stormfront, a white supremacist forum. A random set of
forums posts have been sampled from several subforums and split into sentences. Those sentences
have been manually labelled as containing hate speech or not, according to certain annotation guidelines.hateful-memes-data
Hateful Memes (CS5242 submission mirror)
Mirror of the Facebook Hateful Memes Challenge dataset (Kiela et al., 2020)
used for reproducibility of our CS5242 (NUS) submission.
Contents
img/ — 10,000 PNG images of memes
train.jsonl (8,500), dev_seen.jsonl (500), dev_unseen.jsonl (540),
test_seen.jsonl (1,000), test_unseen.jsonl (2,000)
Provenance
This mirror merges two existing mirrors of the original Meta release:
Label files and most images from… See the full description on the dataset page: https://huggingface.co/datasets/cs5242-hateful-memes/hateful-memes-data.hatecheck
Dataset Card for HateCheck
Dataset Description
HateCheck is a suite of functional test for hate speech detection models.
The dataset contains 3,728 validated test cases in 29 functional tests.
19 functional tests correspond to distinct types of hate. The other 11 functional tests cover challenging types of non-hate.
This allows for targeted diagnostic insights into model performance.
In our ACL paper, we found critical weaknesses in all commercial and academic hate… See the full description on the dataset page: https://huggingface.co/datasets/Paul/hatecheck.korean_hate_speech_copyThe K-MHaS (Korean Multi-label Hate Speech) dataset contains 109k utterances from Korean online news comments labeled with 8 fine-grained hate speech classes or Not Hate Speech class.
The fine-grained hate speech classes are politics, origin, physical, age, gender, religion, race, and profanity and these categories are selected in order to reflect the social and historical context.multi-hatecheck
MultiHateClassification
An MTEB dataset
Massive Text Embedding Benchmark
Hate speech detection dataset with binary
(hateful vs non-hateful) labels. Includes 25+ distinct types of hate
and challenging non-hate, and 11 languages.
Task categoryt2c
Domains
Constructed, Written
Reference
https://aclanthology.org/2022.woah-1.15/
How to evaluate on this task
You can evaluate an embedding model on this dataset… See the full description on the dataset page: https://huggingface.co/datasets/mteb/multi-hatecheck.korean_hate_speech_mergeK-HATERShate_speech_offensive
hate_speech_offensive
This dataset is a version from hate_speech_offensive, splitted into train and test set.
hate_speech18korea_hate_speechK-MHaS는 추가 레이블링 필수
hate_speech_twitter
Dataset Card for Dataset Name
The dataset is designed to analyze and address hate speech within online platforms. It consists of two sets: the training and testing sets. The two datasets have been labeled and categorized instances of hate speech into nine distinct categories.
Dataset Description
The dataset comprises three key features: tweets, labels (with hate speech denoted as 1 and non-hate speech as 0), and categories (behavior, class, disability, ethnicity, gender… See the full description on the dataset page: https://huggingface.co/datasets/thefrankhsu/hate_speech_twitter.miracl-arabickor_hateHuman-annotated Korean corpus collected from a popular domestic entertainment news aggregation platform
for toxic speech detection. Comments are annotated for gender bias, social bias and hate speech.roman_urdu_hate_speech
Dataset Card for roman_urdu_hate_speech
Dataset Summary
The Roman Urdu Hate-Speech and Offensive Language Detection (RUHSOLD) dataset is a Roman Urdu dataset of tweets annotated by experts in the relevant language. The authors develop the gold-standard for two sub-tasks. First sub-task is based on binary labels of Hate-Offensive content and Normal content (i.e., inoffensive language). These labels are self-explanatory. The authors refer to this sub-task as coarse-grained… See the full description on the dataset page: https://huggingface.co/datasets/community-datasets/roman_urdu_hate_speech.hatespeech_detection
HaSpeeDe2
The HaSpeeDe2 dataset collects 8,012 tweets and 500 news headlines annotated for the presence of hate speech, stereotypes and nominal utterance.
The dataset has been used in the context of the HaSpeeDe task (http://www.di.unito.it/~tutreeb/haspeede-evalita20/index.html), organized as part of the EVALITA 2020 evaluation campaign (http://www.evalita.it/2020).
In order to meet the GDPR requirements, texts have been pseudonymized replacing all original IDs in both datasets… See the full description on the dataset page: https://huggingface.co/datasets/evalitahf/hatespeech_detection.hate_speech_labeledhatebrHateBR is the first large-scale expert annotated corpus of Brazilian Instagram comments for hate speech and offensive language detection on the web and social media. The HateBR corpus was collected from Brazilian Instagram comments of politicians and manually annotated by specialists. It is composed of 7,000 documents annotated according to three different layers: a binary classification (offensive versus non-offensive comments), offensiveness-level (highly, moderately, and slightly offensive messages), and nine hate speech groups (xenophobia, racism, homophobia, sexism, religious intolerance, partyism, apology for the dictatorship, antisemitism, and fatphobia). Each comment was annotated by three different annotators and achieved high inter-annotator agreement. Furthermore, baseline experiments were implemented reaching 85% of F1-score outperforming the current literature models for the Portuguese language. Accordingly, we hope that the proposed expertly annotated corpus may foster research on hate speech and offensive language detection in the Natural Language Processing area.MMSoc_HatefulMemeskmhas_korean_hate_speechThe K-MHaS (Korean Multi-label Hate Speech) dataset contains 109k utterances from Korean online news comments labeled with 8 fine-grained hate speech classes or Not Hate Speech class.
The fine-grained hate speech classes are politics, origin, physical, age, gender, religion, race, and profanity and these categories are selected in order to reflect the social and historical context.hate_speech_slovak
Slovak Hate Speech and Offensive Language Database
The dataset contains posts from a social network with human annotations.
Annotations
The posts are marked 1 if the post contain hateful or offensive language, 0 otherwise.
Dataset Creation
The source data were scraped from a social network from a selection of public pages for sport, politics or general discussion. The gathered data were cleaned from span with a text clustering.
The posts were annotated by a… See the full description on the dataset page: https://huggingface.co/datasets/TUKE-KEMT/hate_speech_slovak.