Your New Best Friend | Basics of the Chatbot

Navya Riju
Jun 20, 2019 · 5 min read

You’ve probably heard of a chatbot. It’s being used so much now, in every industry, because the potential is enormous.

And the statistics prove it.

Again and again, the statistics show us that in the next 30 years — chatbots will be everywhere.

“Chatbots represent a new trend in how people access information, make decisions, and communicate. We think that chatbots are the beginning of a new form of digital access, which centers on messaging. Messaging has become a huge component of how we interact with our devices, and how we stay connected with the people, businesses and the day-to-day activities of life. Chatbots bring commerce into this part of our lives, and will open up new opportunities.” — Christie Pitts, Manager — Ventures Development of Verizon Ventures.

Since chatbots are going to be used widely in the future, let’s dive into the basics.

A Chatbot is a Communicative Assistant.

It’s basically an assistant that communicates with us through text messages — an automated system of communication. It can be integrated into websites, instant messengers or applications.

Types of chatbots

Although there are a lot of different types, that generally depends on how they are programmed, we can divide them into two large groups.

Simple chatbots

These chatbots function based on pre-written keywords they understand. These comments have to be manually written by the developer. A problem with this is that if a user asks a question without using a keyword, the chatbot would not be able to understand it.

Smart chatbots

These chatbots use artificial intelligence when they communicate with users. Instead of pre-prepared answers, the robot responds with adequate suggestions on the topic.

Going Deeper — How do Chatbots Work?

An NLP (natural — language-processing) chatbot takes a combination of steps to convert text or speech into data that can be used. Some of the steps include:

Tokenization.

With a string of characters, the natural language processor will divide those words into “tokens” that are useful for the application.

Named entity recognition.

This looks for categories of words — for example, a person’s name.

Normalization.

Goes through processes to find common spelling or errors that could change the meaning.

Speech tagging.

Identifies certain parts of speech — nouns, verbs. Understands how these structures impact meaning.

Sentiment analysis.

Watches and learns the cues to know if the human user is having a good experience or if chatbot should do better

Build better voice apps. Get more articles & interviews from voice technology experts at voicetechpodcast.com

What can chatbots do?

Startups and emerging companies have been incorporating these interactive agents into their daily operations.

Improve customer service.

This is the best option for those who want their customers to either, search for an answer, streamline a process, or wait for an answer from an employee.

Personalize communication.

A chatbot can answer the specific questions that customers could have instead of general answers.

Automate repetitive tasks.

A lot of customers want answers to the same or similar questions, like When you open? What are your locations? It makes the process much faster and more efficient as well.

Now the science of it is cool enough, but let’s look at some real-life examples of chatbots and where they’re being used. (p.s. they’re pretty cool😎)

MedWhat: Medical Diagnosis Chatbot

This chatbot aims to make medical diagnoses faster, easier, and more transparent for both patients and physicians.

NBC: Navigating Headlines

NBC Politics Bot allowed users to engage with the conversational agent via Facebook to identify breaking news topics.

Hipmunk: Traveling

Hipmunk is a platform that allows people to search for travel deals and many of its users turn to it to book flights, hotels, rental cars, or packages.

Whole Foods Chatbot

This chatbot connects with users by providing recipes, products, and cooking inspiration.

Airbnb Chatbot

This chatbot helps answer customer questions about a variety of different things.

Key Takeaways:

  • Chatbots help with communication or just work as assistants as general.
  • They use artifical intelligence and natural language processing.
  • They are being used in a variety of different industries and their applications are widespread.
  • The number of chatbots being used will increase by a huge amount in 30 years.

So long story short — chatbots are pretty cool. In fact, I’ve decided to build my own chatbot using TensorFlow.

I’m still working on this project, so stay tuned for a video and a project demo!

If you enjoyed this article, please give it some claps so I know you liked it!

You can also follow me on LinkedIn to see what I’m up to or sign up for my monthly newsletter to get updates from me:

Voice Tech Podcast

Voice technology interviews & articles. Learn from the experts.

Navya Riju

Written by

Voice Tech Podcast

Voice technology interviews & articles. Learn from the experts.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade