Skip to content
This repository has been archived by the owner on Dec 24, 2021. It is now read-only.

Home

Jump to bottom
Steve Martinelli edited this page Mar 29, 2018 · 8 revisions

Short Name

Create a review analyzer with Watson Discovery

Short Description

Create a cognitive online shopper guide with Watson Discovery using the reviews of the product you're looking to buy

Offering Type

Cognitive

Introduction

We will create a webapp that asks for the link of the product you want and takes the reviews it finds and store them in a database. The app will then upload the reviews to Watson Discovery for you.

Author

By Anthony Amanse and Horea Porutiu

Code

https://github.com/IBM/watson-second-opinion

Demo

  • link to demo video

Video

Overview

In this Code Pattern, we will create a Node.js app that takes the reviews from an online shopping website, Amazon, and feeds them into the Watson Discovery service. The reviews will be stored in a Cloudant or couchdb database. The Watson Discovery service will show the overall sentiments of the reviews. The sample application will do all the reading of reviews for you and will give an overall insight about them. The Code Pattern can be useful to developers that are looking into processing multiple documents with Watson Discovery.

When the reader has completed this Code Pattern, they will understand how to:

  • Interact with Watson Discovery using Watson's Node SDK
  • Build a User Inerface around the result of Watson Discovery
  • Deploy the app in Kubernetes
  • Deploy and connect a CouchDB in the same instance of Kubernetes Cluster

Flow

  1. The user deploys the app in Kubernetes. The user interacts with the User Interface of the app.
  2. The user enters the product ID and the app would start getting the reviews of the Product.
  3. The app then stores the reviews in a CouchDB database for later use.
  4. The app starts to upload the reviews in Watson Discovery.
  5. After Watson Discovery finishes processing the reviews, the app then stores the result (General Sentiment and Top Entities) in the CouchDB. The user will see the result in the UI.

Included components

  • Watson Discovery: A cognitive search and content analytics engine for applications to identify patterns, trends, and actionable insights.
  • Kubernetes Cluster: Create and manage your own cloud infrastructure and use Kubernetes as your container orchestration engine.

Featured technologies

  • Node.js: An open-source JavaScript run-time environment for executing server-side JavaScript code.
  • Databases: Repository for storing and managing collections of data.
  • Cloud: Accessing computer and information technology resources through the Internet.

Blog

http://developer.ibm.com/code/?p=32974&preview=1&_ppp=7827c7a810

Links

Clone this wiki locally