|
|
--- |
|
|
license: mit |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
pipeline_tag: text-classification |
|
|
tags: |
|
|
- sentiment-analysis |
|
|
- keras |
|
|
- lstm |
|
|
- attention |
|
|
- scratch-model |
|
|
--- |
|
|
# 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 |
