Read this in other languages: 한국어.
This pattern is part of the Get started with natural language processing learning path.
Combine the power of a Jupyter Notebook, Cognos Dashboard Embedded, and IBM Watson™ natural language processing to glean useful marketing insight from a vast body of unstructured Facebook data. To help improve brand perception, product performance, customer satisfaction, and audience engagement, take data from a Facebook Analytics export, enrich it with Watson Visual Recognition and Natural Language Understanding, and create interactive charts to outline your findings. Credit goes to Anna Quincy and Tyler Andersen for providing the initial notebook design.
We start with data exported from Facebook Analytics and enrich that data with Watson APIs.
We will use the enriched data to answer questions like:
- What sentiment is most prevalent in the posts with the highest engagement performance?
- What emotion has the higher engagement score on average?
- What are the most common keywords, entities, and objects in your posts?
These types of insights are beneficial for marketing analysts interested in understanding and improving brand perception, product performance, customer satisfaction, and audience engagement. It is important to note that this pattern is meant to be used as a guided experiment, rather than an application with one set output.
The standard Facebook Analytics export features text from posts, articles, and thumbnails, along with standard Facebook performance metrics, such as likes, shares, and impressions. This unstructured content is then enriched with Watson APIs to extract keywords, entities, sentiment, and emotion.
After data is enriched with Watson APIs, there are several ways to analyze it. Watson Studio provides a robust yet flexible method of exploring the Facebook content.
This pattern provides mock Facebook data, a notebook, and comes with several pre-built visualizations to get you started with uncovering hidden insights. When you complete this pattern, you will understand how to:
- Read external data into a Jupyter Notebook via Watson Studio Object Storage and pandas DataFrame.
- Enrich unstructured data using a Jupyter Notebook and Watson Visual Recognition and Natural Language Understanding.
- Use Cognos Dashboard Embedded to explore data and visualize insights.
- A CSV file exported from Facebook Analytics is added to Object Storage.
- Generated code makes the file accessible as a pandas DataFrame.
- The data is enriched with Watson Natural Language Understanding.
- The data is enriched with Watson Visual Recognition.
- Use a dashboard to visualize the enriched data and uncover hidden insights.
Ready to put this code pattern to use? Complete details on how to get started running and using this application are in the README file.
This pattern showed how to combine a Jupyter Notebook, IBM Watson services, Cloud Object Storage and dashboards to glean useful marketing insight from a vast body of unstructured Facebook data. The pattern is part of the Get started with natural language processing learning path.