Chevron Left
Back to Sentiment Analysis with Deep Learning using BERT

Learner Reviews & Feedback for Sentiment Analysis with Deep Learning using BERT by Coursera Project Network

4.5
stars
390 ratings

About the Course

In this 2-hour long project, you will learn how to analyze a dataset for sentiment analysis. You will learn how to read in a PyTorch BERT model, and adjust the architecture for multi-class classification. You will learn how to adjust an optimizer and scheduler for ideal training and performance. In fine-tuning this model, you will learn how to design a train and evaluate loop to monitor model performance as it trains, including saving and loading models. Finally, you will build a Sentiment Analysis model that leverages BERT's large-scale language knowledge. Note: This course works best for learners who are based in the North America region. We’re currently working on providing the same experience in other regions....

Top reviews

FR

Oct 11, 2020

Clean, clear and helpful. Thanks a lot!

Would also be nice to see the approaches to tune BERT for the particular task (e.g. custom tokenization, pre-processing of data, etc.)

GB

Jul 27, 2020

Thanks to Mr.Ari Anastassiou

Sentiment Analysis with Deep Learning using BERT! is been really a wonderful project .Enjoyed it

Filter by:

76 - 82 of 82 Reviews for Sentiment Analysis with Deep Learning using BERT

By Ovi S

•

Jun 2, 2020

Good

By M M A

•

Jul 26, 2020

Ok

By Venkata N C K

•

Jun 1, 2020

.

By Seema A

•

May 23, 2021

All in all good. But it would have been much better with more explanations about the code.

By PRASHANT K

•

Jun 28, 2021

It's not up to coursera Standards. Could have been done much much better. Only one good thing can out of it for me that he has provided one or two good reference for reading about BERT.

By Raj P

•

Jan 2, 2021

I didn't learn anything new here. This code and explanation is available on the web free of cost.

By Saurabh T

•

Jul 23, 2022

Till 'Tokenization and Encoding the data' part, explanation of the code was good. But from 'Setting up BERT pretrained model' part, code explanation was not done properly. Instructor was not giving proper explanation of the BERT parameters that are used in the code.