| # Twitter-roBERTa-base for Hate Speech Detection | |
| This is a roBERTa-base model trained on ~58M tweets and finetuned for hate speech detection with the TweetEval benchmark. | |
| This model is specialized to detect hate speech against women and immigrants. | |
| **NEW!** We have made available a more recent and robust hate speech detection model here: [https://huggingface.co/cardiffnlp/twitter-roberta-base-hate-latest](https://huggingface.co/cardiffnlp/twitter-roberta-base-hate-latest) | |
| - Paper: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf). | |
| - Git Repo: [Tweeteval official repository](https://github.com/cardiffnlp/tweeteval). | |
| ## Example of classification | |
| ```python | |
| from transformers import AutoModelForSequenceClassification | |
| from transformers import TFAutoModelForSequenceClassification | |
| from transformers import AutoTokenizer | |
| import numpy as np | |
| from scipy.special import softmax | |
| import csv | |
| import urllib.request | |
| # Preprocess text (username and link placeholders) | |
| def preprocess(text): | |
| new_text = [] | |
| for t in text.split(" "): | |
| t = '@user' if t.startswith('@') and len(t) > 1 else t | |
| t = 'http' if t.startswith('http') else t | |
| new_text.append(t) | |
| return " ".join(new_text) | |
| # Tasks: | |
| # emoji, emotion, hate, irony, offensive, sentiment | |
| # stance/abortion, stance/atheism, stance/climate, stance/feminist, stance/hillary | |
| task='hate' | |
| MODEL = f"cardiffnlp/twitter-roberta-base-{task}" | |
| tokenizer = AutoTokenizer.from_pretrained(MODEL) | |
| # download label mapping | |
| labels=[] | |
| mapping_link = f"https://raw.githubusercontent.com/cardiffnlp/tweeteval/main/datasets/{task}/mapping.txt" | |
| with urllib.request.urlopen(mapping_link) as f: | |
| html = f.read().decode('utf-8').split("\n") | |
| csvreader = csv.reader(html, delimiter='\t') | |
| labels = [row[1] for row in csvreader if len(row) > 1] | |
| # PT | |
| model = AutoModelForSequenceClassification.from_pretrained(MODEL) | |
| model.save_pretrained(MODEL) | |
| text = "Good night 😊" | |
| text = preprocess(text) | |
| encoded_input = tokenizer(text, return_tensors='pt') | |
| output = model(**encoded_input) | |
| scores = output[0][0].detach().numpy() | |
| scores = softmax(scores) | |
| # # TF | |
| # model = TFAutoModelForSequenceClassification.from_pretrained(MODEL) | |
| # model.save_pretrained(MODEL) | |
| # text = "Good night 😊" | |
| # encoded_input = tokenizer(text, return_tensors='tf') | |
| # output = model(encoded_input) | |
| # scores = output[0][0].numpy() | |
| # scores = softmax(scores) | |
| ranking = np.argsort(scores) | |
| ranking = ranking[::-1] | |
| for i in range(scores.shape[0]): | |
| l = labels[ranking[i]] | |
| s = scores[ranking[i]] | |
| print(f"{i+1}) {l} {np.round(float(s), 4)}") | |
| ``` | |
| Output: | |
| ``` | |
| 1) not-hate 0.9168 | |
| 2) hate 0.0832 | |
| ``` | |