Twitter September 2022 (RoBERTa-base, 169M)

This is a RoBERTa-base model trained on 168.86M tweets until the end of September 2022 (15M tweets increment). More details and performance scores are available in the TimeLMs paper.

Below, we provide some usage examples using the standard Transformers interface. For another interface more suited to comparing predictions and perplexity scores between models trained at different temporal intervals, check the TimeLMs repository.

For other models trained until different periods, check this table.

Preprocess Text

Replace usernames and links for placeholders: "@user" and "http". If you're interested in retaining verified users which were also retained during training, you may keep the users listed here.

def preprocess(text):
    preprocessed_text = []
    for t in text.split():
        if len(t) > 1:
            t = '@user' if t[0] == '@' and t.count('@') == 1 else t
            t = 'http' if t.startswith('http') else t
        preprocessed_text.append(t)
    return ' '.join(preprocessed_text)

Example Masked Language Model

from transformers import pipeline, AutoTokenizer

MODEL = "cardiffnlp/twitter-roberta-base-sep2022"
fill_mask = pipeline("fill-mask", model=MODEL, tokenizer=MODEL)
tokenizer = AutoTokenizer.from_pretrained(MODEL)

def pprint(candidates, n):
    for i in range(n):
        token = tokenizer.decode(candidates[i]['token'])
        score = candidates[i]['score']
        print("%d) %.5f %s" % (i+1, score, token))

texts = [
    "So glad I'm <mask> vaccinated.",
    "I keep forgetting to bring a <mask>.",
    "Looking forward to watching <mask> Game tonight!",
]
for text in texts:
    t = preprocess(text)
    print(f"{'-'*30}\n{t}")
    candidates = fill_mask(t)
    pprint(candidates, 5)

Output:

------------------------------
So glad I'm <mask> vaccinated.
1) 0.60140  not
2) 0.15077  getting
3) 0.12119  fully
4) 0.02203  still
5) 0.01020  all
------------------------------
I keep forgetting to bring a <mask>.
1) 0.05812  charger
2) 0.05040  backpack
3) 0.05004  book
4) 0.04548  bag
5) 0.03992  lighter
------------------------------
Looking forward to watching <mask> Game tonight!
1) 0.39552  the
2) 0.28083  The
3) 0.02029  End
4) 0.01878  Squid
5) 0.01438  this

Example Tweet Embeddings

from transformers import AutoTokenizer, AutoModel, TFAutoModel
import numpy as np
from scipy.spatial.distance import cosine
from collections import Counter

def get_embedding(text):  # naive approach for demonstration
  text = preprocess(text)
  encoded_input = tokenizer(text, return_tensors='pt')
  features = model(**encoded_input)
  features = features[0].detach().cpu().numpy() 
  return np.mean(features[0], axis=0) 


MODEL = "cardiffnlp/twitter-roberta-base-sep2022"
tokenizer = AutoTokenizer.from_pretrained(MODEL)
model = AutoModel.from_pretrained(MODEL)

query = "The book was awesome"
tweets = ["I just ordered fried chicken 🐣", 
          "The movie was great",
          "What time is the next game?",
          "Just finished reading 'Embeddings in NLP'"]

sims = Counter()
for tweet in tweets:
    sim = 1 - cosine(get_embedding(query), get_embedding(tweet))
    sims[tweet] = sim

print('Most similar to: ', query)
print(f"{'-'*30}")
for idx, (tweet, sim) in enumerate(sims.most_common()):
    print("%d) %.5f %s" % (idx+1, sim, tweet))

Output:

Most similar to:  The book was awesome
------------------------------
1) 0.98914 The movie was great
2) 0.96194 Just finished reading 'Embeddings in NLP'
3) 0.94603 What time is the next game?
4) 0.94580 I just ordered fried chicken 🐣

Example Feature Extraction

from transformers import AutoTokenizer, AutoModel, TFAutoModel
import numpy as np

MODEL = "cardiffnlp/twitter-roberta-base-sep2022"
tokenizer = AutoTokenizer.from_pretrained(MODEL)

text = "Good night 😊"
text = preprocess(text)

# Pytorch
model = AutoModel.from_pretrained(MODEL)
encoded_input = tokenizer(text, return_tensors='pt')
features = model(**encoded_input)
features = features[0].detach().cpu().numpy() 
features_mean = np.mean(features[0], axis=0) 
#features_max = np.max(features[0], axis=0)

# # Tensorflow
# model = TFAutoModel.from_pretrained(MODEL)
# encoded_input = tokenizer(text, return_tensors='tf')
# features = model(encoded_input)
# features = features[0].numpy()
# features_mean = np.mean(features[0], axis=0) 
# #features_max = np.max(features[0], axis=0)