README.md

metadata

language: en
datasets:
  - tweet_eval
widget:
  - text: Covid cases are increasing fast!
model-index:
  - name: cardiffnlp/twitter-roberta-base-sentiment-latest
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: tweet_eval
          type: tweet_eval
          config: sentiment
          split: validation
        metrics:
          - type: accuracy
            value: 0.7715
            name: Accuracy
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNzEyZDhlYTA4ZTYwYTg0ZWIwZDlmYzIyYWQ3YjY4NGQ1ZjVjYzJjODk2Mjc4YWRiNjU2NzhmMmJmNDUzNTIxMiIsInZlcnNpb24iOjF9.75SSI8U0ZlfehMx7Zh6LotmSB_Zp9taCnKCi23SVVHghX--eM0jy6OWtqf4IWxkEwb6yoTNxcyoOw_Av6UNTCg
          - type: f1
            value: 0.7606415252231301
            name: F1 Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMWIxYzJhNjgxNTM5ZTRjNDJmNTU2NGFlOWE2ZjViODk3NWJkMzA0YTMyYmUzNjdhM2RjNzhkYTViMDRjNDcyZiIsInZlcnNpb24iOjF9.wIjAJNlzzk-M8tsigytlLRYy0uQDGo3Qy1F7afmk5b1XrGnAy1E4Mw-JHDtbZ2uYZiPx0grbOOxL-yT_4DCSCg
          - type: f1
            value: 0.7715000000000001
            name: F1 Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiOTVhZDA4ZWM3YzgzYjVlOTk2ODkxNzQzNjBjMjBlMmZiM2QwN2QyYTVjMDUxNWU3ZTQ2MGZhNGIxYTY3NGI0ZSIsInZlcnNpb24iOjF9.-VYy5OLXwpaoiD4HR7wBjmV5izt2yTXvRbp93cs7jPvPEij7rkidjd-HpVaHMvIOLoTjxnKozFf0pmNQF06WBg
          - type: f1
            value: 0.7732314418938615
            name: F1 Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNmRmNjUyMjU3ZTljYmViMWRiNDMzODE4YTU3ZjU2YzQ3MDQyZGRhYjBmYzU0Yjk0Yjk3MzVmYjNjM2U5YzFjZCIsInZlcnNpb24iOjF9.BguI5gGX0H4P8LNTAayaBxv7rUYqvepCyKo9rOIsEXsTVN9N-J9IfjUGjptpKJBpOXEi_MGFLV6H7IJUyhdbDA
          - type: precision
            value: 0.7508336175429541
            name: Precision Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzM2NDNlZGE2ZDNmYmMyZTU0OWYzOGYwYzM1NWE1YzIzNjBkZjA0NzkxYjY1ZWI4OTM5NWVkZTZkNjgzZTQ1MSIsInZlcnNpb24iOjF9.3YBiMV0HMcEtr4lFDe4BFhTkyfL0EL6Xk3V9ICNOtOMdNgDChRMnphsYh6WaUILJNA0qlmHzh7h_RpciLwMDBw
          - type: precision
            value: 0.7715
            name: Precision Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNDk5NDk0OGFlNTI1NDhkMTY3NWZmYmYwODBiY2M2YmI0YjkxOWJmYWZiZTViNWQ3ZDk2Mjk3OTNiMDMxMmEwMiIsInZlcnNpb24iOjF9._Zk6Kwarj5Jv_rLX9fp-Np6qwUZwyQ7dD-ylnCJtXEm-ZkarYemTLZqjq_1nWATD3vQcYoHlXD0RFOzYQxSaCw
          - type: precision
            value: 0.7782372190165424
            name: Precision Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjI5YzIwODcwYjUwMTY1MDVjNThlMGUxMWUzMTQ5MGE5Nzk5ZmZlNTM1ZTQzYjJhNTFkYzkyYzQzOTUwZGRkNiIsInZlcnNpb24iOjF9.OoGtZoogQHq49Vh_MZMO4yASGembVB1xDE216tT_JQGV3zh0_IRdJ9eztxXOn3Hx8qxrQwSEwzKZKp3gj4l3Dw
          - type: recall
            value: 0.7762803886221606
            name: Recall Macro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGI5YTI4OWI5ZGVkOWUyYzc3NzI1M2I1MWUzN2JmOGQ3ODlmN2MwMDI0MmI0ZjkxZWZjNDZjOTNkODg4ZmFlNCIsInZlcnNpb24iOjF9.fkdes7mIwaxI_8AVJuahiZoRq0MZzzMsjDddn8trtxi37fHCMEX86hf__Kmbs5AxrgtkJA3fd4H5iKcEaq1MBA
          - type: recall
            value: 0.7715
            name: Recall Micro
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDkwZTQzNzhiNzgyODU1YTVjYzFiMTg4ZGZiYjg5ZTBlYTNkNWM5MWMyZTFkMjQyZDA0OGU3ODUwNzQ0MzNiNiIsInZlcnNpb24iOjF9.JtK5c3OOO9ryDKsddzAykHcj8nF-LvA96oF3MPTqB8FtyWuWQEBJAMhID-xhCgGTfEtD-n_LggDBeww1AZQOBg
          - type: recall
            value: 0.7715
            name: Recall Weighted
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzc5OTY0NWYxNDM5ZDEyMDM2ZDdlYjQ0YWIwMzU2YTQ0YTBjMmE3NGEzOGIzNmY5ODEwNzQ3M2YyOWY3NDVkMCIsInZlcnNpb24iOjF9.gpw2NXq5Z6zj4JXXBDkETnY6dQxKDBLyQP3nGaKeRhTA_sQ7zud0xDiKKSJa8dckE4tSS6fjW-9xoAyvlxFxAw
          - type: loss
            value: 0.525364875793457
            name: loss
            verified: true
            verifyToken: >-
              eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmVhNTE5MThiNTMxMzZlOThiNWFhOGYzYjBkZjUzZjUwYWM5NGIxZjc1ZjIzMGRjZmIzZmVhNDAxZjVjNGUyZSIsInZlcnNpb24iOjF9.W3vo0Hdh0tL8kfWDGUjtYj6AUJCt8xYaW6WEiICUPhLVeRaUab_rwSGLiEQ5Sy1ccnOC38gEzZvrPlxs0VDlDg

Twitter-roBERTa-base for Sentiment Analysis - UPDATED (2022)

This is a RoBERTa-base model trained on ~124M tweets from January 2018 to December 2021, and finetuned for sentiment analysis with the TweetEval benchmark. The original Twitter-based RoBERTa model can be found here and the original reference paper is TweetEval. This model is suitable for English.

• Reference Paper: TimeLMs paper.
• Git Repo: TimeLMs official repository.

Labels: 0 -> Negative; 1 -> Neutral; 2 -> Positive

This sentiment analysis model has been integrated into TweetNLP. You can access the demo here.

Example Pipeline

from transformers import pipeline
sentiment_task = pipeline("sentiment-analysis", model=model_path, tokenizer=model_path)
sentiment_task("Covid cases are increasing fast!")

[{'label': 'Negative', 'score': 0.7236}]

Full classification example

from transformers import AutoModelForSequenceClassification
from transformers import TFAutoModelForSequenceClassification
from transformers import AutoTokenizer, AutoConfig
import numpy as np
from scipy.special import softmax
# 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)
MODEL = f"cardiffnlp/twitter-roberta-base-sentiment-latest"
tokenizer = AutoTokenizer.from_pretrained(MODEL)
config = AutoConfig.from_pretrained(MODEL)
# PT
model = AutoModelForSequenceClassification.from_pretrained(MODEL)
#model.save_pretrained(MODEL)
text = "Covid cases are increasing fast!"
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 = "Covid cases are increasing fast!"
# encoded_input = tokenizer(text, return_tensors='tf')
# output = model(encoded_input)
# scores = output[0][0].numpy()
# scores = softmax(scores)
# Print labels and scores
ranking = np.argsort(scores)
ranking = ranking[::-1]
for i in range(scores.shape[0]):
    l = config.id2label[ranking[i]]
    s = scores[ranking[i]]
    print(f"{i+1}) {l} {np.round(float(s), 4)}")

Output:

1) Negative 0.7236
2) Neutral 0.2287
3) Positive 0.0477