https://github.com/furk4neg3/textemotionrecognition

In this project, I've created AI models to predict emotion based on texts. I've used RNN and transfer learning for that. Best model works with 96% accuracy.
https://github.com/furk4neg3/textemotionrecognition

artificial-intelligence deep-learning machine-learning nlp rnn rnn-tensorflow tensorflow tensorflow2 transfer-learning

Last synced: about 2 months ago
JSON representation

In this project, I've created AI models to predict emotion based on texts. I've used RNN and transfer learning for that. Best model works with 96% accuracy.

• Host: GitHub
• URL: https://github.com/furk4neg3/textemotionrecognition
• Owner: furk4neg3
• Created: 2024-08-03T22:33:19.000Z (5 months ago)
• Default Branch: main
• Last Pushed: 2024-08-05T12:52:03.000Z (5 months ago)
• Last Synced: 2024-08-05T23:56:08.151Z (5 months ago)
• Topics: artificial-intelligence, deep-learning, machine-learning, nlp, rnn, rnn-tensorflow, tensorflow, tensorflow2, transfer-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 93.8 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Text Emotion Recognition

In this project, I've created AI models to predict emotion based on texts. I've used RNN and transfer learning for that. Best model works with 96% accuracy. All data preparation and preprocessing is done by me. Dataset is from Kaggle, link can be found in the notebook.

IMPORTANT NOTE: In the last model, I was going to use TinyBERT model. I tried it and it was taking too long to train, so I switched to USE. But in the naming part, it's still Model 5 (TinyBERT). To fix this issue, I should run the notebook again only changing the name part on the last 2 or 3 cells, which is not worth the time (it's going to take ~3 hours). Please be aware of this naming issue.