This repository will not be updated. The repository will be kept available in read-only mode.
In this example, we will use Watson Discovery News in order to query articles written about Bitcoin and visualize the sentiment of the articles. This should act as a baseline for integrating Watson Discovery into your own application. The use cases are endless, with Watson Discovery, and especially the "news" collection, you can harness the power of advanced queries in order to gain many insights.
- User creates an instance of Watson Discovery.
- User run the provided Jupyter notebook with Watson Studio.
- The Jupyter notebook leverages Watson Discovery News to visualize data sentiment and date.
Sign up for IBM's Watson Studio. After signing in, create a new, basic project – give it a name, and create a new object storage service if prompted (the lite option will work fine).
Head over to IBM Cloud, if prompted, login with the same credentials as above. From the dashboard, click Create Resource and search for "Discovery" in the catalog. Click on the Discovery card, and click Create.
From Watson Studio, navigate to the project you created previously.
- In the
Assets
tab, select theCreate notebook
option. - Select the
From URL
tab. - Enter a name for the notebook.
- Optionally, enter a description for the notebook.
- Enter this Notebook URL: https://raw.githubusercontent.com/IBM/crypto-discovery-news-sentiment-analysis/master/notebooks/crypto-analysis.ipynb
Once the notebook has been created, navigate to the cell with Watson Discovery credentials and enter your own. To find your credentials, navigate to your Discovery service, click on the menu item labeled Credentials, generate a new set if none exists yet. Now, you can run the notebook and analyze the results.
See examples/example_notebook.ipynb for a full run of the notebook with output.
Below is a snapshot of the type of analysis performed, showing both sentiment and date for cryptocurrencies.
- Data Analytics Code Patterns: Enjoyed this Code Pattern? Check out our other Data Analytics Code Patterns
- With Watson: Want to take your Watson app to the next level? Looking to utilize Watson Brand assets? Join the With Watson program to leverage exclusive brand, marketing, and tech resources to amplify and accelerate your Watson embedded commercial solution.
- Watson Studio: Master the art of data science with IBM's Watson Studio
- Check out the blog post!
This code pattern is licensed under the Apache Software License, Version 2. Separate third party code objects invoked within this code pattern are licensed by their respective providers pursuant to their own separate licenses. Contributions are subject to the Developer Certificate of Origin, Version 1.1 (DCO) and the Apache Software License, Version 2.