• Length:
    3 Weeks
  • Effort:
    2–4 hours per week
  • Price:

    Add a Verified Certificate for $99 USD

  • Institution
  • Subject:
  • Level:
  • Language:
  • Video Transcript:
  • Course Type:
    Self-paced on your time

Associated Programs:


This course provides an introduction to developing and deploying cognitive applications. You should have basic knowledge of object-oriented programming, how to use the command line, Node.js, and IBM Watson Assistant (formerly known as Watson Conversation).

You also need:

If you want to build the chatbot application locally, install Node.js and npm.

If not familiar with IBM Watson Assistant, take the How to Build Chatbots and Make Money course first.

About this course

Skip About this course

By enrolling in this course, chances are you've studied artifical intelligence, built chatbots and have perhaps even used Watson Assistant along the way. But did you know that you can turbocharge your chatbot's IQ with IBM Watson Discovery, a service designed to reveal the hidden value in your data? Discovery specializes in taking your data--structured or unstructured--and extracting from it answers and patterns.

For example, if you have a large repository, the contents of which could answer customer questions, you've got the makings of a great FAQ chatbot.

In this course, you'll learn how to build queries in Discovery, which allows you to surface answers and patterns from large repositories of data. You'll next learn to use Discovery to extract insights from a set of hotel reviews. Then, to make that data come to life, you'll integrate Discovery with other Watson services to create a chatbot that can tell you about the best hotels in a certain US city. By using these Watson services, you'll add more layers of analysis to help you find the best hotel.

You'll build your chatbot application with the following Watson services:

  • Assistant
  • Discovery
  • Tone Analyzer
  • Personality Insights

By the end of this course, you will have built a fully functioning AI-powered chatbot. Moreover, you should be able to apply the services taught here to your own data sets, enabling you to create sophisticated chatbots of your own.

What you'll learn

Skip What you'll learn
  • Apply your foundational concepts of AI and machine learning into building and programming chatbots
  • Create a chatbot application that interacts in natural language in IBM Cloud
  • Synthesize data that can be queried to extract sentiment, concepts, entities, and taxonomy by using Watson Discovery
  • Reveal the emotions, sentiment, and customer preferences found in hotel reviews by using Tone Analyzer and Personality Insights and feed that data to the chatbot
  • Lab 1: Build a Watson chatbot
    • Watson Assistant overview
    • Deploy Watson Assistant
    • Import the workspace
    • Create intents, entities, and dialog
    • Apply the Jump to action
    • Add multiple response conditions for a specific intent
    • Add responses for other intents
    • Test the chatbot
  • Lab 2: Build queries by using Watson Discovery

    • Watson Discovery overview
    • Access the news collection in the Discovery tool
    • Understand the data structure
    • Query the data by using filters
    • Query the data by using the query parameter
    • Query the data by using aggregation
    • Retrieve longer passages from the data
    • Train Discovery to improve relevancy
    • Lab 3: Enhance a chatbot with Discovery

    • Get the starter code and credentials

    • Integrate Discovery with the chatbot

    • Test the application

    • Lab 4: Gain insights by using Discovery

    • Get the data into Discovery

    • Find basic insights in the data

    • Lab 5: Analyze the tone from hotel reviews

    • Watson Tone Analyzer overview

    • Deploy the Tone Analyzer service

    • Analyze the tone in hotel review

    • Test the tone analysis

    • Lab 6: Analyze customer preferences

    • Watson Personality Insights overview

    • Deploy the Personality Insights service

    • Get the personality profile

    • Test the application

    • Final exam

Meet your instructors

Rav Ahuja
AI and Data Science Program Director

Pursue a Verified Certificate to highlight the knowledge and skills you gain
$99 USD

View a PDF of a sample edX certificate
  • Official and Verified

    Receive an instructor-signed certificate with the institution's logo to verify your achievement and increase your job prospects

  • Easily Shareable

    Add the certificate to your CV or resume, or post it directly on LinkedIn

  • Proven Motivator

    Give yourself an additional incentive to complete the course

  • Support our Mission

    edX, a non-profit, relies on verified certificates to help fund free education for everyone globally

Who can take this course?

Unfortunately, learners from one or more of the following countries or regions will not be able to register for this course: Iran, Cuba and the Crimea region of Ukraine. While edX has sought licenses from the U.S. Office of Foreign Assets Control (OFAC) to offer our courses to learners in these countries and regions, the licenses we have received are not broad enough to allow us to offer this course in all locations. edX truly regrets that U.S. sanctions prevent us from offering all of our courses to everyone, no matter where they live.