Movie review prediction Challenge

#1

I am having 87% accuracy in this challenge. How can I improve it further ?
Here is my code-
https://colab.research.google.com/drive/1S8G1pZDZgMXfGblO-COX-j5MgkhVoNqH?usp=sharing

#2

Hey @sanchit123manchanda, it is great that you achieved 87% accuracy. 87% is good accuracy on this dataset. For increasing more you can use LSTMs, bidirectional RNN for achieving better accuracies.

Happy Learning :slight_smile:

#3

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.

#4

hey @sanchit123manchanda ,
we see that you have re opened your doubt . I would like to suggest you the same thing as my friend @Aayushkh_333 did in his reply stated above. You are currently using only types of naive bayes algorithm on this , its not that they aren’t good. they do perform really well. But in such kind of challenges you need to understand the context / meaning of a sentence to get better prediction. And that can only be done using word embeddings , so if you gonna stay with naiver bayes algorithms , search about word embeddings first , understand them and think how can they be used here.
Else, if you are familiar with deep learning architectures like RNN , LSTM, BiLSTM , then go with them , thay will surely provide you with amazing and out of the benchmark results.

I hope this would have resolved your doubt.
Thank You and Happy Learning :slightly_smiling_face:.