Smart chatbots rely on artificial intelligence when they communicate with users. Instead of pre-prepared answers, the robot responds with adequate suggestions on the topic. In addition, all the words said by the customers are recorded for later processing. However, the Forrester report “The State of Chatbots” points out that artificial intelligence is not a magic and is not yet ready to produce marvelous experiences for users on its own. On the contrary, it requires a huge work:
Please check out our main directory with 1376 live chat bot examples (an overview as maintained by developers themselves), our vendor listing with 256 chat bot companies and chat bot news section with already more than 370 articles! Our research tab contains lots of papers on chat bots, 1,166 journals on chat bots and 390 books on chat bots. This research section also shows which universities are active in the chat bot field, indicates which publishers are publishing journals on humanlike conversational AI and informs about academic events on chat bots. Also, check out our dedicated tab for awards, contest and games related to the chat bot field, various forums like our AI forum by chat bot enthusiasts and add any chat bot as created by yourself and your colleagues to our chat bot directory. Please do not forget to register to join us in these exciting times.
The idea was to permit Tay to “learn” about the nuances of human conversation by monitoring and interacting with real people online. Unfortunately, it didn’t take long for Tay to figure out that Twitter is a towering garbage-fire of awfulness, which resulted in the Twitter bot claiming that “Hitler did nothing wrong,” using a wide range of colorful expletives, and encouraging casual drug use. While some of Tay’s tweets were “original,” in that Tay composed them itself, many were actually the result of the bot’s “repeat back to me” function, meaning users could literally make the poor bot say whatever disgusting remarks they wanted.
Reports of political interferences in recent elections, including the 2016 US and 2017 UK general elections, 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, 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, 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.
Chatbots talk in almost every major language. Their language (Natural Language Processing, NLP) skills vary from extremely poor to very clever intelligent, helpful and funny. The same counts for their graphic design, sometimes it feels like a cartoonish character drawn by a child, and on the other hand there are photo-realistic 3D animated characters available, which are hard to distinguish from humans. And they are all referred to as ‘chatbots’. If you have a look at our chatbot gallery, you will immediately notice the difference.
Sometimes it is hard to discover if a conversational partner on the other end is a real person or a chatbot. In fact, it is getting harder as technology progresses. A well-known way to measure the chatbot intelligence in a more or less objective manner is the so-called Turing Test. This test determines how well a chatbot is capable of appearing like a real person by giving responses indistinguishable from a human’s response.
In the early 90’s, the Turing test, which allows determining the possibility of thinking by computers, was developed. It consists in the following. A person talks to both the person and the computer. The goal is to find out who his interlocutor is — a person or a machine. This test is carried out in our days and many conversational programs have coped with it successfully.
Companies and customers can benefit from internet bots. Internet bots are allowing customers to communicate with companies without having to communicate with a person. KLM Royal Dutch Airlines has produced a chatbot that allows customers to receive boarding passes, check in reminders, and other information that is needed for a flight. Companies have made chatbots that can benefit customers. Customer engagement has grown since these chatbots have been developed.
The first formal instantiation of a Turing Test for machine intelligence is a Loebner Prize and has been organized since 1991. In a typical setup, there are three areas: the computer area with typically 3-5 computers, each running a stand-alone version (i.e. not connected with the internet) of the participating chatbot, an area for the human judges, typically four persons, and another area for the ‘confederates’, typically 3-5 voluntary humans, dependent on the number of chatbot participants. The human judges, working on their own terminal separated from one another, engage in a conversation with a human or a computer through the terminal, not knowing whether they are connected to a computer or a human. Then, they simply start to interact. The organizing committee requires that conversations are restricted to a single topic. The task for the human judges is to recognize chatbot responses and distinguish them from conversations with humans. If the judges cannot reliably distinguish the chatbot from the human, the chatbot is said to have passed the test.
“Major shifts on large platforms should be seen as an opportunities for distribution. That said, we need to be careful not to judge the very early prototypes too harshly as the platforms are far from complete. I believe Facebook’s recent launch is the beginning of a new application platform for micro application experiences. The fundamental idea is that customers will interact with just enough UI, whether conversational and/or widgets, to be delighted by a service/brand with immediate access to a rich profile and without the complexities of installing a native app, all fueled by mature advertising products. It’s potentially a massive opportunity.” — Aaron Batalion, Partner at Lightspeed Venture Partners