Twitter-roBERTa-base for Emotion Recognition

This is a RoBERTa-base model trained on ~58M tweets and finetuned for emotion recognition with the TweetEval benchmark.

• Paper: TweetEval benchmark (Findings of EMNLP 2020) .
• Git Repo: Tweeteval official repository .

New! We just released a new emotion recognition model trained with more emotion types and with a newer RoBERTa-based model. See twitter-roberta-base-emotion-multilabel-latest and TweetNLP for more details.

Example of classification

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='emotion'
MODEL = f"cardiffnlp/twitter-roberta-base-{task}"

tokenizer = AutoTokenizer.from_pretrained(MODEL)

# download label mapping
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 = "Celebrating my promotion ?"
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 = "Celebrating my promotion ?"
# 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) joy 0.9382
2) optimism 0.0362
3) anger 0.0145
4) sadness 0.0112