Sentiment Analysis from Scratch (LSTM + Attention)
This is a sentiment analysis model built entirely from scratch using a bidirectional LSTM architecture with an attention mechanism. The tokenizer is also trained from scratch on the dataset of 1.6 million tweets.
Dataset Link
https://www.kaggle.com/datasets/mdraselsarker/sentiment140-dataset-with-1-6-million-tweets
Kaggle Notebook Link
https://www.kaggle.com/code/mastershomya/sentiment-analysis-deep-bilstm
- Downloads last month
- 18
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://MasterShomya/Tweets_Sentiment_Analyzer")