Let us stop talking about machine learning, neural networks, natural language processing and all the fancy tech. We need to be clear about what chatbots are and what they are not.
It is entirely our fault. As technologists we got too carried away with the technological potential. Two minutes into a “why chatbots” conversation and we are digging a hole for ourselves trying to explain natural language processing, artificial intelligence and all the other really exciting things.
Things didn’t quite work out that way.
Is that because chatbots are not a useful technology?
Chatbots can be extremely useful by doing very little and often work best when used in conjunction with other technologies like websites or apps. That, however, is not that exciting to talk about.
This post by Intercom is a great example of not getting carried away. They admit that one of the most useful things the chatbot does is categorise contacts into either exiting customers or new customers. Based on that, users were routed to the right team. Problem solved, money saved. No AI involved.
Someone is wrong on the web.
Try to search “what is a chatbot” on Google.
Google starts out with two definitions and both are highly problematic.
The dictionary definition says chatbots are “designed to simulate conversation with human users”. That makes it sound like chatbots are supposed to sound human-like or be indistinguishable from a human.
The Wikipedia definition is even worse. A chatbot is a computer program or an artificial intelligence. As if those two things are somehow separate.
Scroll down the page and most results are a mismatch of confusing chatbots with the technology one could use to develop chatbots (e.g. natural language processing or the even more enigmatic AI) or a problem chatbots are meant to solve (e.g. customer support).
To give you an idea of what clarity looks like let us search for the definition of a website.
We need to talk about chatbots in the same way.
Chatbots are computer programs that interact with a user using a conversational paradigm.
That’s it. Everything else comes afterwards.
This is significant because it does away with a lot of the noise and it simplifies the discussion about the utility of chatbots.
Is a conversational paradigm suitable? The answers could be:
- Yes, because it offers another channel to communicate with our users (e.g. Messenger)
- Yes, because it is the easiest way to solve our user’s problem (e.g. customer support)
- No, because the task at hand is best solved through a “classic” web interface.
and so on and so forth.
How you will then build a chatbot, whether you should use NLP or any other fancy technology (blockchain anyone?)is an entirely different issue.
Let’s start talking about chatbots as potentially very simple things that can do potentially very useful things. Let’s stop talking about AI, machine learning and all the rest until they are actually involved in the process in a significant way.
At GreenShoot Labs we help organisations define and develop chatbot-centric solutions.
Chatbots have an identity problem. It’s time we got things straight. was originally published in Hacker Noon on Medium, where people are continuing the conversation by highlighting and responding to this story.