Unable to see performance of custom sentiment analysis in Language studio

Wassila-2299 0 Reputation points
2024-06-19T18:21:45.93+00:00

I want to use custom sentiment analysis in azure language studio.

I have used the auto-label on my unlabeled data, reviewed the results and set a training job. the training succeeds but when looking into the details I have no performances (F1 score to 0%, same for precision and recall).

As input I have Positive (2384)  ,Neutral (2221)  ,Negative (3799).

Can you please help me figure out what am I doing wrong.

Thank you for your help.

Azure AI services
Azure AI services
A group of Azure services, SDKs, and APIs designed to make apps more intelligent, engaging, and discoverable.
2,577 questions

1 answer

Sort by: Most helpful
Most helpful Newest Oldest
  1. santoshkc 6,310 Reputation points Microsoft Vendor
    2024-06-20T07:06:30.02+00:00

    Hi @Wassila-2299,

    Thank you for reaching out to Microsoft Q&A forum!

    It's great to hear that you have successfully trained a custom sentiment analysis model in Language Studio. However, it seems that you are unable to see the performance metrics for your model.

    To view the performance metrics for your custom sentiment analysis model, you can follow these steps:

    1. Go to your project page in Language Studio.
    2. Select Model performance from the menu on the left side of the screen.
    3. In this page you can only view the successfully trained models, F1 score of each model and model expiration date. You can select the model name for more details about its performance. Models only include evaluation details if there was test data selected while training the model.

    For more info, please look into: View your model's performance.

    If you do not see any performance metrics, it is possible that your model did not perform well on the test data. You can try retraining your model to improve its performance. I hope you followed instructions while training the model:

    See the project development lifecycle for more information.

    I hope this helps! Thank you.

    0 comments