Update README.md

README.md

@@ -1,4 +1,4 @@
-# Twitter-roBERTa-base
+# Twitter-roBERTa-base for Sentiment Analysis
 
 This is a roBERTa-base model trained on ~58M tweets and finetuned for the Sentiment Analysis task at Semeval 2018. 
 For full description: [_TweetEval_ benchmark (Findings of EMNLP 2020)](https://arxiv.org/pdf/2010.12421.pdf). 
@@ -6,6 +6,15 @@ To evaluate this and other models on Twitter-specific data, please refer to the
 
 ## Example of classification
 
+# 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)
+
 ```python
 from transformers import AutoModelForSequenceClassification
 from transformers import TFAutoModelForSequenceClassification
@@ -37,6 +46,7 @@ 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()