Chatbot Definition, Types, Pros & Cons, Examples

What Is a Chatbot?

A chatbot is a computer program that simulates human conversation through voice commands or text chats or both. Chatbot, short for chatterbot, is an artificial intelligence (AI) feature that can be embedded and used through any major messaging application.

There are a number of synonyms for chatbot, including "talkbot," "bot," "IM bot," "interactive agent" or "artificial conversation entity."

Understanding Chatbots

The progressive advance of technology has seen an increase in businesses moving from traditional to digital platforms to transact with consumers. Convenience through technology is being carried out by businesses by implementing AI techniques on their digital platforms. One AI technique that is growing in its application and use is chatbots. Some examples of chatbot technology are virtual assistants like Amazon's Alexa and Google Assistant, and messaging apps, such as WeChat and Facebook's Messenger.

A chatbot is an automated program that interacts with customers as a human would and costs little to nothing to engage with. Chatbots attend to customers at all times of the day and week and are not limited by time or a physical location. This makes its implementation appealing to a lot of businesses that may not have the manpower or financial resources to keep employees working around the clock.

Types of Chatbots

A chatbot works in a couple of ways: set guidelines and machine learning (ML).

Set Guidelines Chatbot

A chatbot that functions with a set of guidelines in place is limited in its conversation. It can only respond to a set number of requests and vocabulary and is only as intelligent as its programming code. An example of a limited bot is an automated banking bot that asks the caller some questions to understand what the caller wants to do.

The bot would make a command like “Please tell me what I can do for you by saying account balances, account transfer, or bill payment.” If the customer responds with "credit card balance," the bot would not understand the request and would proceed to either repeat the command or transfer the caller to a human assistant.

Over time, chatbots have evolved with new AI advancements and are far more responsive to human interaction than chatbots based on set guidelines.

Machine Learning Chatbot

A chatbot that functions through machine learning has an artificial neural network inspired by the neural nodes of the human brain. The bot is programmed to self-learn as it is introduced to new dialogues and words. In effect, as a chatbot receives new voice or textual dialogues, the number of inquiries that it can reply to and the accuracy of each response it gives increases.

Meta (as Facebook's parent company is now known) has a machine learning chatbot that creates a platform for companies to interact with their consumers through the Messenger application. Using the Messenger bot, users can buy shoes from Spring, order a ride from Uber, and have conversations with The New York Times on news issues of the day. If a user asked The New York Times through the app a question like “What’s new today?” or “What do the polls say?” the bot would reply to the request.

Chatbots are used in a variety of sectors and built for different purposes. There are retail bots designed to pick and order groceries, weather bots that give you weather forecasts of the day or week, and simply friendly bots that just talk to people in need of a friend.

The fintech sector also uses chatbots to make consumers’ inquiries and applications for financial services easier. In 2016, a small business lender in Montreal, Thinking Capital, uses a virtual assistant to provide customers with 24/7 assistance through Facebook Messenger. A small business hoping to get a loan from the company needs only answer key qualification questions asked by the bot in order to be deemed eligible to receive up to $300,000 in financing.

Advantages and Disadvantages of Chatbots

Chatbots are convenient for providing customer service and support 24 hours a day, 7 days a week. They also free up phone lines and are far less expensive over the long run than hiring people to perform support. Using AI and natural language processing, chatbots are becoming better at understanding what customers want and providing the help they need. Companies also like chatbots because they can collect data about customer queries, response times, satisfaction, and so on.

Chatbots, however, are still limited. Even with natural language processing, they may not fully comprehend a customer's input and may provide incoherent answers. Many chatbots are also limited in the scope of queries that they are able to respond to. This may lead to frustration with a lack of emotion, sympathy, and personalization given fairly generic feedback. In addition to customer dissatisfaction with not reaching a human being, chatbots can be expensive to implement and maintain, especially if they must be customized and updated often.

Examples of Chatbots

Today, chatbots are ubiquitous on corporate websites, e-commerce platforms, and other customer-facing sites online (on the web or via app). These can help with customer support such as how to return or replace an item, how to request a refund, and so on.

Chatbots have also been implemented to help with public policy and inform citizens if they have certain questions. For example, in response to the COVID-19 pandemic, several health chatbots were created by governments and healthcare providers. A recent study of such chatbots identified five key applications of the current health chatbots, which were:

• disseminating health information and knowledge;
• self-triage and personal risk assessment;
• monitoring exposure and notifications;
• tracking COVID-19 symptoms and health aspects; and
• combating misinformation and fake news

Furthermore, these technologies can ask and answer questions, create health records and history of use, complete forms and generate reports, and take simple actions. Nonetheless, the use of health chatbots poses many challenges both at the level of the social system (i.e., consumers’ acceptability) as well as the technical system (i.e., design and usability).