Classifying sentiments in text by using Word Embedding and the model is built Tensorflow2.
In this project News Headlines Dataset For Sarcasm Detection by Rishabh Misra used to create a deep learning model which will be able to classify a sentence as sarcastic or not.
While doing all of this we will go through:
preprocess text for neural networksWord Embedding and how to visualize them using Tensorflow ProjectorGlobalAveragePooling1D and FlattenThis deep learning model is trained using GPU and to work in the same environment having packages with versions which were used while making this notebook, go to Kaggle where the kernel is saved.
The dataset is divided into 97% for training, 1.5% for validation and testing respectively. The model is trained for 20 epochs.
Model’s performance on training and validation datasets.
Model’s performance on testing dataset.
Model’s poor performance on testing set might be because of small number of testing samples or our model might be facing overfitting issue on training and validation. So there is room for improvement.
Visualizing the word embedding learned by the model using Tensorflow Projector
