You can use a chatbot to talk to your customers and automate messages. But one chatbot has more functionalities than the other chatbot. And some do understand the context better, where other chatbots don’t understand the context at all. How advanced a chatbot is depends on the type of user input and the ability of the chatbot to appropriately respond to it.
In this blog post, we will shortly look at what a chatbot is and which types of chatbots there are.
Table of Contents
What is a chatbot?
A chatbot produces simulated conversations in which the human user inputs something and the chatbot makes a response. It is a way to automate the conversations that you are having with customers. For example, you could use a chatbot to save costs on customer service or to increase sales. Also, one of the main benefits of a chatbot that there is always someone answering your customers’ question, even in the middle of the night.
If you want to learn more about chatbots and what they are, you need to check out this post.
There are three types of chatbots:
- Menu/Button-based chatbots
- Keyword recognition-based chatbots
- Contextual chatbots
Menu/Button-based chatbots
Menu/Button-based chatbots are the most basic type of chatbots on the market today. Instead of giving the user the possibility to give free text input, the user is limited to a number of buttons.
Pros
- Sufficient for answering standard questions, which make up for 80% of support queries
- Good for qualification of leads
For example, the chatbot could ask “Which department do you need” with three buttons “Sales”, “Customer Service” and “Support”. When the user clicks on of the buttons, he will be referred to the right department. - Control over the flow of the conversation
The user will never get in a position where the chatbot does not understand his input
Cons
- Chatbot falls short when users want to ask more advanced questions
An example of a menu/button-based chatbot is Landbot. Landbot is software which you can build chatbots with. They only allow users to interact with the chatbots through buttons.
Keyword recognition-based chatbots
Keyword-recognition based chatbots are an extension of menu/button-based chatbots. With keyword recognition-based chatbots users can interact by giving free text input. The chatbot then analyses the text on specific keywords and based on those keywords, gives an appropriate response.
For example, when a user asks “What are the benefits of a car X?”, the chatbot could recognise the keywords “benefits” and “car X”, and give a list of possible benefits of using the specific car.
Pros
- Gives users more freedom in input
- Users can ask more advanced questions
- More natural conversations
Cons
- The user can get in a position where the chatbot cannot answer the question
If a user asks “What are the drawbacks of auto X?” and the chatbot does not recognize the words, it cannot respond to the question, which could lead to dissatisfaction.
In general, with keyword recognition-based chatbots you have less control over the flow of the conversation than with menu/button-based chatbots. But, often keyword-recognition based chatbots are used to control the flow of the conversation with buttons, but at the same time giving the user the possibility to ask other questions.
Most chatbots built on Facebook Messenger are keyword recognition-based chatbots. An example is the EpicReads chatbot. This is a chatbot that advises book lovers on which books to read.
Contextual chatbots
Contextual chatbots are an extension of keyword recognition-based chatbots. Also, they are the most advanced type of chatbots. These chatbots use Machine Learning and Artificial Intelligence techniques to interact with users.
Contextual chatbots remember conversations with specific users and are capable enough to improve their responses based on what a user is asking and how the user asks it (context of the question). For example, when a user wants to order a pizza, a contextual chatbot could remember his last order and already offer him a pizza based on his previous purchase.
Pros
- More natural conversations
- Users can ask more advanced questions
Cons
- Higher costs, because of Machine Learning and Artificial Intelligence techniques
An example of a contextual chatbot is the Hipmunk chatbot. Hipmunk is a chatbot for booking airplane tickets. It has the possibility to remember your flight preferences from the last time you visited the chatbot.
Which type of chatbot is best for your business?
To determine which chatbot is best for your business, you need to do the following:
- Determine the goal of your chatbot
What should your chatbot do? Does I need to answer simple questions? Or does it need to have deep conversations with your customers?
- Who is in control of the conversation?
Is the customer in control of the conversation or you? Do you want your customers to ask questions freely? Or do you determine which actions they get to do?
- Which channels do you want to use?
Which channels do you want to use for your chatbot? Do you only want a chatbot on your website? Or also on social media channels, like Facebook? And if so, do the website and the other channels need to be integrated?
- How many time do you have and what is your budget?
The time and budget you have for the project is extremely important. For example, contextual chatbots cost way more time and money than menu/button-based chatbots.
Conclusion
- A chatbot produces simulated conversations in which the human user inputs something and the chatbot makes a response
- There are three types of chatbots: Menu/Button-based, Keyword recognition-based and Contextual chatbots
Now a question for you: which type of your chatbot are you familiar with? Leave a comment!
