Skip to content

yesdeepakmittal/Sentiment-Classification-using-BERT

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Sentiment Classification using BERT

Sentiment Classification is a common business use case for any company that sells products or services. Companies utilize the sentiment information of the consumers to improve their products/services and even build new products based on the feedback received. It helps in making rational decisions.

Approach & Objective

We will build a Sentiment Classification model using BERT. We will need a labeled dataset for model training and evaluation. If the data is not labeled, we have to label it manually.

  • Data Collection
  • Data Labelling
  • Convert target variables into the numeric form
  • Text Preprocessing
    • tokenization(subword tokenization handled by WordPiece tokenizer)
    • text encoding
    • text embedding
  • Model training
  • Model Evaluation
  • Model Serving

About

Sentiment Classification using BERT

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published