This model is a fine-tuned version of
cardiffnlp/twitter-roberta-base-2022-154m
for binary hate-speech classification.
A combination of 13 different hate-speech datasets in the English language were used to fine-tune the model.
More details in the
reference paper
.
Dataset
Accuracy
Macro-F1
Weighted-F1
hatEval, SemEval-2019 Task 5: Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter
0.5831
0.5646
0.548
ucberkeley-dlab/measuring-hate-speech
0.9273
0.9193
0.928
Detecting East Asian Prejudice on Social Media
0.9231
0.6623
0.9428
Call me sexist, but
0.9686
0.9203
0.9696
Predicting the Type and Target of Offensive Posts in Social Media
0.9164
0.6847
0.9098
HateXplain
0.8653
0.845
0.8662
Large Scale Crowdsourcing and Characterization of Twitter Abusive BehaviorLarge Scale Crowdsourcing and Characterization of Twitter Abusive Behavior
0.7801
0.7446
0.7614
Multilingual and Multi-Aspect Hate Speech Analysis
0.9944
0.4986
0.9972
Hate speech and offensive content identification in indo-european languages
0.8779
0.6904
0.8706
Are You a Racist or Am I Seeing Things?
0.921
0.8935
0.9216
Automated Hate Speech Detection
0.9423
0.9249
0.9429
Hate Towards the Political Opponent
0.8783
0.6595
0.8788
Hateful Symbols or Hateful People?
0.8187
0.7833
0.8323
Overall
0.8766
0.7531
0.8745
Usage
Install tweetnlp via pip.
pip install tweetnlp
Load the model in python.
import tweetnlp
model = tweetnlp.Classifier("cardiffnlp/twitter-roberta-base-hate-latest")
model.predict('I love everybody :)')
>> {'label': 'NOT-HATE'}
Reference paper - Model based on:
@inproceedings{antypas-camacho-collados-2023-robust,
title = "Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation",
author = "Antypas, Dimosthenis and
Camacho-Collados, Jose",
booktitle = "The 7th Workshop on Online Abuse and Harms (WOAH)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.woah-1.25",
pages = "231--242"
}
Runs of cardiffnlp twitter-roberta-base-hate-latest on huggingface.co
3.1K
Total runs
0
24-hour runs
-22
3-day runs
-544
7-day runs
-405
30-day runs
More Information About twitter-roberta-base-hate-latest huggingface.co Model
More twitter-roberta-base-hate-latest license Visit here:
twitter-roberta-base-hate-latest huggingface.co is an AI model on huggingface.co that provides twitter-roberta-base-hate-latest's model effect (), which can be used instantly with this cardiffnlp twitter-roberta-base-hate-latest model. huggingface.co supports a free trial of the twitter-roberta-base-hate-latest model, and also provides paid use of the twitter-roberta-base-hate-latest. Support call twitter-roberta-base-hate-latest model through api, including Node.js, Python, http.
twitter-roberta-base-hate-latest huggingface.co is an online trial and call api platform, which integrates twitter-roberta-base-hate-latest's modeling effects, including api services, and provides a free online trial of twitter-roberta-base-hate-latest, you can try twitter-roberta-base-hate-latest online for free by clicking the link below.
cardiffnlp twitter-roberta-base-hate-latest online free url in huggingface.co:
twitter-roberta-base-hate-latest is an open source model from GitHub that offers a free installation service, and any user can find twitter-roberta-base-hate-latest on GitHub to install. At the same time, huggingface.co provides the effect of twitter-roberta-base-hate-latest install, users can directly use twitter-roberta-base-hate-latest installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
twitter-roberta-base-hate-latest install url in huggingface.co: