Other companies explore ways they can use chatbots internally, for example for Customer Support, Human Resources, or even in Internet-of-Things (IoT) projects. Overstock.com, for one, has reportedly launched a chatbot named Mila to automate certain simple yet time-consuming processes when requesting for a sick leave.[31] Other large companies such as Lloyds Banking Group, Royal Bank of Scotland, Renault and Citroën are now using automated online assistants instead of call centres with humans to provide a first point of contact. A SaaS chatbot business ecosystem has been steadily growing since the F8 Conference when Facebook's Mark Zuckerberg unveiled that Messenger would allow chatbots into the app.[32] In large companies, like in hospitals and aviation organizations, IT architects are designing reference architectures for Intelligent Chatbots that are used to unlock and share knowledge and experience in the organization more efficiently, and reduce the errors in answers from expert service desks significantly.[33] These Intelligent Chatbots make use of all kinds of artificial intelligence like image moderation and natural language understanding (NLU), natural language generation (NLG), machine learning and deep learning.
Another reason is that Facebook, which has 900 million Messenger users, is expected to get into bots. Many see this as a big potential opportunity; where Facebook goes, the rest of the industry often follows. Slack, which lends itself to bot-based services, has also grown dramatically to two million daily users, which bot makers and investors see as a potentially lucrative market.
I will not go into the details of extracting each feature value here. It can be referred from the documentation of rasa-core link that I provided above. So, assuming we extracted all the required feature values from the sample conversations in the required format, we can then train an AI model like LSTM followed by softmax to predict the next_action. Referring to the above figure, this is what the ‘dialogue management’ component does. Why LSTM is more appropriate? — As mentioned above, we want our model to be context aware and look back into the conversational history to predict the next_action. This is akin to a time-series model (pls see my other LSTM-Time series article) and hence can be best captured in the memory state of the LSTM model. The amount of conversational history we want to look back can be a configurable hyper-parameter to the model.

Conversational bots can help a business’s customers with difficult transactions, plus collect data and give recommendations. For example, a conversational bot integrated to an airline’s website can answer questions regarding flight availability, rebook tickets, fees and suggest add-ons like hotels. Though a conversational bot may not be able to finish the exchanges, it could still be able to gather preliminary data and pass it on to the next available customer care agent. In both cases, the airline will save considerable time in its call center.
Love them or hate them, chatbots are here to stay. Chatbots have become extraordinarily popular in recent years largely due to dramatic advancements in machine learning and other underlying technologies such as natural language processing. Today’s chatbots are smarter, more responsive, and more useful – and we’re likely to see even more of them in the coming years.

Facebook has jumped fully on the conversational commerce bandwagon and is betting big that it can turn its popular Messenger app into a business messaging powerhouse. The company first integrated peer-to-peer payments into Messenger in 2015, and then launched a full chatbot API so businesses can create interactions for customers to occur within the Facebook Messenger app. You can order flowers from 1–800-Flowers, browse the latest fashion and make purchases from Spring, and order an Uber, all from within a Messenger chat.
Reports of political interferences in recent elections, including the 2016 US and 2017 UK general elections,[3] have set the notion of botting being more prevalent because of the ethics that is challenged between the bot’s design and the bot’s designer. According to Emilio Ferrara, a computer scientist from the University of Southern California reporting on Communications of the ACM,[4] the lack of resources available to implement fact-checking and information verification results in the large volumes of false reports and claims made on these bots in social media platforms. In the case of Twitter, most of these bots are programmed with searching filter capabilities that target key words and phrases that reflect in favor and against political agendas and retweet them. While the attention of bots is programmed to spread unverified information throughout the social media platform,[5] it is a challenge that programmers face in the wake of a hostile political climate. Binary functions are designated to the programs and using an Application Program interface embedded in the social media website executes the functions tasked. The Bot Effect is what Ferrera reports as when the socialization of bots and human users creates a vulnerability to the leaking of personal information and polarizing influences outside the ethics of the bot’s code. According to Guillory Kramer in his study, he observes the behavior of emotionally volatile users and the impact the bots have on the users, altering the perception of reality.
On the other hand, early adoption can be somewhat of a curse. In 2011, many companies and individuals, myself included, invested a lot of time and money into Google+, dubbed to be bigger than Facebook at the time. They acquired over 10 million new users within the first two weeks of launch and things were looking positive. Many companies doubled-down on growing a community within the platform, hopeful of using it as a new and growing acquisition channel, but things didn't exactly pan out that way.
The process of building a chatbot can be divided into two main tasks: understanding the user's intent and producing the correct answer. The first task involves understanding the user input. In order to properly understand a user input in a free text form, a Natural Language Processing Engine can be used.[36] The second task may involve different approaches depending on the type of the response that the chatbot will generate.

One pertinent field of AI research is natural language processing. Usually, weak AI fields employ specialized software or programming languages created specifically for the narrow function required. For example, A.L.I.C.E. uses a markup language called AIML, which is specific to its function as a conversational agent, and has since been adopted by various other developers of, so called, Alicebots. Nevertheless, A.L.I.C.E. is still purely based on pattern matching techniques without any reasoning capabilities, the same technique ELIZA was using back in 1966. This is not strong AI, which would require sapience and logical reasoning abilities.