Roberta Base Stocktwits Finetuned

🚀 Sentiment Inferencing model for stock related commments

A sentiment analysis model for stock comments, fine - tuned on a large - scale dataset to accurately classify bullish and bearish sentiments.

🚀 Quick Start

This model is a sentiment inferencing tool for stock - related comments. It was developed by NUS ISS students Frank Cao, Gerong Zhang, Jiaqi Yao, Sikai Ni, Yunduo Zhang. You can try it out by inputting text on the inference API, such as 'red' and 'green'.

Check the code on github

✨ Features

• Fine - Tuned Model: Fine - tuned with the roberta - base model on 3200000 comments from Stocktwits, labeled as 'Bullish' or 'Bearish'.
• Accurate Classification: Capable of accurately classifying the sentiment of stock - related comments.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import RobertaForSequenceClassification, RobertaTokenizer
from transformers import pipeline
import pandas as pd
import emoji

# the model was trained upon below preprocessing
def process_text(texts):

  # remove URLs
  texts = re.sub(r'https?://\S+', "", texts)
  texts = re.sub(r'www.\S+', "", texts)
  # remove '
  texts = texts.replace(''', "'")
  # remove symbol names
  texts = re.sub(r'(\#)(\S+)', r'hashtag_\2', texts)
  texts = re.sub(r'(\$)([A-Za-z]+)', r'cashtag_\2', texts)
  # remove usernames
  texts = re.sub(r'(\@)(\S+)', r'mention_\2', texts)
  # demojize
  texts = emoji.demojize(texts, delimiters=("", " "))

  return texts.strip()
  
tokenizer_loaded = RobertaTokenizer.from_pretrained('zhayunduo/roberta-base-stocktwits-finetuned')
model_loaded = RobertaForSequenceClassification.from_pretrained('zhayunduo/roberta-base-stocktwits-finetuned')

nlp = pipeline("text-classification", model=model_loaded, tokenizer=tokenizer_loaded)

sentences = pd.Series(['just buy','just sell it',
                      'entity rocket to the sky!',
                      'go down','even though it is going up, I still think it will not keep this trend in the near future'])
# sentences = list(sentences.apply(process_text))  # if input text contains https, @ or # or $ symbols, better apply preprocess to get a more accurate result
sentences = list(sentences)
results = nlp(sentences)
print(results) # 2 labels, label 0 is bearish, label 1 is bullish

📚 Documentation

Description

This model is fine - tuned with the roberta - base model on 3200000 comments from Stocktwits. The comments are labeled by users as 'Bullish' or 'Bearish'. You can try inputting text that individual investors might say on an investment forum in the inference API.

Training information

• Batch size: 32
• Learning rate: 2e - 5

📄 License

This project is licensed under the Apache - 2.0 license.