Chat, Social, and Survey Interactions Using AI Idea Analysis

Editor’s note: Ben is a speaker at ODSC East 2019 this May in Boston! Be sure to check out his talk, “Continuous Improvement of Chat, Social, and Survey Interactions Using AI Idea Analysis.”

“The future of communicating with customers rests in engaging with them through every possible channel: phone, email, chat, web, and social networks. Customers are discussing a company’s products and brand in real time. Companies need to join the conversation.” — Marc Benioff

Today’s customers demand a superior experience every time they interact with a brand, regardless of platform or channel. 86% of customers say that they’ll pay more for a better experience, and 89% of customers began doing business with a competitor after a bad experience. Navigating across platforms is challenging enough for businesses, and it’s made even more difficult by the fact that interactions between customers and businesses are increasingly done in conversations. Furthermore, only very specific steps of the customer journey are done through form-fills or transactions that result in structured data. The rest of the data generated results in natural language, or unstructured data. In fact, Gartner cites that data volume will grow by 800% in the next 5 years. In order for businesses to be able to deliver the best possible interactions and to understand what their customers want, natural language AI solutions and AI idea analysis that can handle all of this data and transform it into something meaningful are required.

[Related article: Introduction to Clinical Natural Language Processing]

Imagine a world where a relatively small team of business experts and analysts could actually have an understanding of the ideas that customers are communicating and which ideas are helping to move customers through the purchase funnel. Or which ideas in a chat conversation need a specific response to delight a customer. Or which newly discovered ideas need to be addressed by a specific area of the business, such as website support or product quality. Deep understanding of what’s happening inside all of those customer conversations or comments is critical to building a successful business.

Traditionally, supervised natural language solutions have been difficult and expensive to build and maintain. Unsupervised systems typically operate off of word count, and result in categorization or interpretations that are close to gibberish for the human evaluating the results. Handling language is complex, and machine learning models need to evolve to address some specific challenges.

  • Context is critical: “Foundation” is very different for Neutrogena than it is for Ryland Homes.
  • The order of words matter: “Help me please, my account shut off,” needs a very different response than, “Please help me shut off my account.”
  • Understanding synonyms and phrase synonyms is important to be able to handle all of the different ways that people talk.

[Related article: Essential NLP Tools, Code, and Tips]

Gamalon is next-generation unsupervised learning for natural language that learns from data and can be guided through abstract supervision in a GUI. Gamalon reads customer messages across any format, interprets, and surfaces the ideas in those messages, and helps you take the next best action for those customers. It can automatically discover new issues and continuously monitors topics as they evolve, and surface the information visually or be shared back as structured data that can be handled by existing company systems. Because Gamalon was built to be transparent and easily editable, it gets smarter faster and is easier to maintain.

It’s now possible to deliver the best possible experience by knowing what your customers are saying at scale. Whether the use case is improved chat, faster product improvement cycles, or customer service improvements, the ability to implement natural language processing quickly and easily is here.

At ODSC East 2019 this April 30 to May 3, Gamalon will be sharing the latest in idea learning technology during their talk “Continuous Improvement of Chat, Social, and Survey Interactions Using AI Idea Analysis.”

About Gamalon: From 2013 to 2017 Gamalon received the largest single contract for the next generation of machine learning from DARPA. With a foundational advance in machine learning developed in collaboration with leading groups at MIT, Berkeley, Stanford, and Columbia, and over 40 patent filings, Gamalon was named one of the 50 Smartest Companies by MIT Technology Review in 2017, and in 2018 became a World Economic Forum Technology Pioneer.

— — —

Read more data science articles on, including tutorials and guides from beginner to advanced levels! Subscribe to our weekly newsletter here and receive the latest news every Thursday.



Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
ODSC - Open Data Science

ODSC - Open Data Science


Our passion is bringing thousands of the best and brightest data scientists together under one roof for an incredible learning and networking experience.