Use advanced NLU to determine sellers’ quality
Lean how to use Watson Natural Language Understanding to analyze sentiment and emotion of customer reviews
This code pattern requires a basic understanding of data refinery and uses the dataset created in this tutorial, Collect, cleanse, and enhance your data. Therefore, you should complete the tutorial before starting this code pattern.
In any e-commerce website, the product sellers have a rating scale of (0 to 5 stars) which are given by customers based on the product that’s been purchased. Taking this rating into account, the customers gain some insight about the seller and can determine if they wish to buy from a particular seller. In this pattern, we’ll be analyzing more parameters such as sentiment analysis of reviews and deriving more insightful rating for sellers.
With the advert rise in e-commerce websites, customer satisfaction has an impact on every aspect of an e-commerce business. The customer satisfaction of any given product distributed by a particular seller can be measured with the help of two major metrics:
- Average rating given by customers on a product
- Reviews representing a customer’s sentiment on the product offered by a seller
In this code pattern, we’ll curate more insightful ratings of sellers by extracting product reviews, analyzing the sentiment and emotion behind the review (using Watson Natural Language Understanding) and deriving a score. This score will later be compared against the delay in the delivery of a given product. And finally, we’ll derive a seller quality rating from 0 to 5.
After completing this code pattern, you will understand how to:
- Use advanced NLP to analyze text and extract meta-data from content such as sentiment, emotion, and relations.
- Run small pieces of code to process your data and immediately view the results with Jupyter Notebook.
- Use Data Refinery to prepare training data for a machine learning task.
- Build interactive dashboards and produce visualizations directly from your data (in real-time with Embedded Dashboard).
- Create a connection for the refined data in Db2 into IBM Watson Studio project in IBM Cloud Pak for Data or IBM Cloud.
- Setup Jupyter Notebook that reads the dataset from the IBM Db2 Connection.
- Run the Algorithm from Jupyter Notebook that computes the seller rating with the help of Watson Natural Language Understanding on IBM Cloud Pak for Data or IBM Cloud.
- Visualize insights from the data using Watson Embedded Dashboard on IBM Cloud Pak for Data or IBM Cloud.
Get the detailed instructions in the README file. These steps will show you how to:
- Download the Dataset
- Create Watson Natural Language Understanding Service
- Create a Project
- Add Db2 Connection to the Project
- Prepare and Run the Jupyter Notebook
- Add Embedded Dashboard to the Project
- Visualize the Dashboard