Humanized chatbot: how to give your bot personality

A humanized chatbot uses artificial intelligence to optimize communication between companies and customers, in addition to establishing a friendly relationship between both parties.
Humanization is a key point for the success of the strategy and involves defining a personality for the bot, for that it is necessary to take care of the tone of voice, visual representation, transparency, among other characteristics that we will address in this content.
Imagine getting in touch with a clinic and being seen by a robot that can check the available times for consultation almost instantly and schedule the procedure right after. Incredible, right?

This is possible with the development of a humanized and intelligent chatbot, which manages to solve demands from the simplest to the most complex in a practical way and without the need for human intervention.

Unlike employees, chatbots do not need breaks for coffee or lunch. They are also not absent due to illnesses, holidays or even natural disasters that can put human life at risk.

IBM estimates that chatbots reduce customer relationship costs by up to 30%. In addition to financial savings, artificial intelligence can be programmed to cross-sell a company’s service portfolio or upsell the catalog with recommendations based on a customer’s previous orders and preferences.

The strategy is on the rise and the Gartner Institute predicts that, by 2022, 72% of interactions between company and customer will be completely driven by automatic mechanisms, such as chatbots.

In 2019, 61 thousand bots were developed by 85 Brazilian companies that responded to a Mobile Time survey. The bots were responsible for the traffic of about 1 billion messages sent per month, twice as much as in 2017, which shows the trend of an increasingly conversational relationship between companies and users. The data are available on the 2019 Brazilian Bot Ecosystem Map.

What is a humanized chatbot

The chatbot is a robot that uses artificial intelligence technology and machine learning to enable automated and efficient service, helping companies to provide 24/7 customer service.

It represents a major evolution in the relationship between people, brands and technology. A humanized chatbot uses artificial intelligence to learn the commands and processes that must be attended to.

In addition, it has a more personal approach, personalized according to the brand identity. In this way, it approaches a service performed by a human being, only with the speed of an automated process and without compromising the productivity of employees.

Types of chatbots

There are chatbots that are based on rules and flows and others based on artificial intelligence.

The first refers to the cases in which the answers are already conditioned by means of a button, as in “To consult your balance, type 1; to speak to the service, type 2 ”. It would basically be the evolution of this type of contact. A response that leaves the established flow is unable to be answered by the bot.

In the second case, the robot is able to learn from the questions and interactions that are carried out to answer them in the future, through the concept that we call machine learning. According to Sinch’s cases, chatbots based on machine learning are able to respond by themselves up to 80% of calls.

A system that does not take advantage of all the possibilities of artificial intelligence, as in the first example we gave, results in an extremely mechanical dialogue and has a much more robotic appearance.

To have a humanized chatbot it is necessary to develop a personality for your bot from a planning with the appropriate tactics, as in the following items:

Voice tone

Every brand needs to have a tone of voice, which defines the personality and language that will be used to speak to customers.

Each human being has a particular way of communicating, but people adapt to different situations. Nobody talks to another person at a meeting of friends in the same way that he writes a scientific article, for example.

The same goes for the chatbot: the ideal is that interactions are personalized according to the brand identity and the purpose of the service.

It is important to have a language similar to that used in everyday life, in a natural and less robotic way. Another strategy that brings good results is to adopt a positive and friendly language, which responds kindly to consumer demands.

Speaking “the same language” as your consumer may seem easy, but it is usually one of the main difficulties when developing a chatbot and requires continuous improvement. So analyze how your customer communicates. If your audience uses emojis, for example, your bot should also take this more informal approach.

Humanization

When talking about chatbots, one of the first things that comes to mind is standardized interactions. In fact, the idea is to look like a conversation between acquaintances and not with a machine.

One of the main challenges of humanization is to make the responses not look like the automatic responses from search engines. Therefore, avoid giving responses that are cold and too limited.

It is necessary to make the client understand that your company (the bot) is interested in helping you to solve a certain problem. At the end of the service, asking if the problem has been solved or thanking the contact are some ways to humanize the contact.

The power of the unexpected

Listening to something unexpected makes us pay more attention to what is being said. If you say “good morning”, expect to get a simple “good morning” back, right? Receiving a response other than that would be unusual.

The intention of the chatbot is that the person is encouraged to remain in the interaction, and this type of unexpected response is a way to keep the person interested in the chat.

Siri, Apple’s virtual assistant, is a good example. It interacts to help you accomplish tasks, organize your information and even answer questions. In addition, she is full of personality and was known for her unexpected and humorous responses.

When she says she is sad, for example, she gives several amusing answers, such as “You can cry, if you want. My aluminosilicate glass surface is tear-proof ”or“ I would offer a shoulder to cry on… if I had one ”.

For this to happen, it is necessary to carry out a mega work of mapping human language and configuring intentions within the robot. That way, he is able to respond according to the different scenarios.

This implies that companies want to get to know their customers more deeply and are willing to configure the bot for all these occasions.

Visual representation

Many brands have a visual representation of their virtual assistants, that is, they give a face to them in order to have a more humanized service.

This is the case of Bela, an Avon bot created to talk to resellers and future resellers. This strategy is a great opportunity to reinforce your branding and get closer to customers.

Transparency

It is not because we are talking about humanized chatbot that this means that the company must pretend that the service is being done by a human being, ok? In fact, being transparent and honest is essential for successful communication.

There is nothing wrong with assuming that the service is being done by a friendly and helpful robot, this should even be made clear from the beginning. You can start the conversation with “Hello, I’m NAME, virtual assistant for the COMPANY. I am here to answer your questions about SUBJECT. Shall we start? ”, For example.

If, in the middle of the way, the bot is no longer able to respond to the customer’s demands, the technology must be able to identify this need and warn the consumer that he is passing the contact on to a specialist who will continue the service.