https://github.com/shakilgithub20/classifying_textual_emotions

https://github.com/shakilgithub20/classifying_textual_emotions

keras loss-functions metrics nlp numpy numpy-arrays optimizer tensorflow

Last synced: 2 months ago
JSON representation

• Host: GitHub
• URL: https://github.com/shakilgithub20/classifying_textual_emotions
• Owner: Shakilgithub20
• Created: 2021-10-07T09:24:52.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2021-10-07T09:31:16.000Z (over 3 years ago)
• Last Synced: 2024-10-11T11:30:11.258Z (3 months ago)
• Topics: keras, loss-functions, metrics, nlp, numpy, numpy-arrays, optimizer, tensorflow
• Language: Jupyter Notebook
• Homepage: https://nbviewer.org/github/Shakilgithub20/Classifying_Textual_Emotions/blob/main/Classifying%20Textual%20Emotions.ipynb
• Size: 508 KB
• Stars: 4
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Classifying Textual Emotions using Neural Networks

As the amount of textual data grows at an exponential rate, it becomes increasingly vital to construct models to assess text data automatically, prompting a slew of text categorization studies. The Neural Network (CNN) has recently been used for text classification and has demonstrated to be fairly successful.

# Parameters:

 Loss : poission,

 Optimizer : Adam,

 Activation functions : Sigmoid,

 Metrics: msle

 Output Layer: 6.

# Outcome: 

The validation process consisted of several phases that probed the parameter training methods described above. In this section, we specify the results of each phase. In order to assess the quality of the prediction, we used several figures of merit. In this study, the performance keras model tested good. With the default configuration, loss (1.0176) whereas, obtained accuracy (0.5482).