README.md

metadata

title: Twitter Sentiment Analysis
emoji: ⚡
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 4.37.2
app_file: app.py
pinned: false
license: mit

Twitter Sentiment Analysis

This project implements a sentiment analysis model to predict the sentiment (positive or negative) of tweets. An LSTM-based model has been trained on 1.6 million tweets.

Project Structure

• 01. Data Preparation:

  • Data Collection: The dataset consisting 1.6 million tweets has been collected from here.
  • Data Cleaning & Preprocessing:
    • Removed stopwords
    • Applied Lemmatization
    • Vectorized the lemmatized data utilizing "TextVectorization" from keras
    • Saved the Vectorizer for utilizing later in the app

• 02. Model Training:

  • A Bidirectional LSTM model with an embedding layer has been trained on the preprocessed data.

• 03. App Deployment:

  • Developed a web-app with Gradio interface
  • Deployed the App in HuggingFace Spaces

• requirements.txt: Contains the dependencies needed for the project:

  • pandas
  • tensorflow==2.15.0
  • nltk
  • gradio

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference