Chatbots of the future will have advanced capabilities in five key areas: natural language processing (NLP), natural language understanding, contextual awareness, anticipate customer needs, and sentiment analysis. Natural Language Processing is the process a machine goes through when translating, summarizing, contextualizing, and analyzing text – or the same process that Google Translate uses to translate text. With natural language understanding, developers can analyze semantic features of text input such as categories, concepts, emotion, entities, keywords, metadata, relations, semantic roles, and sentiment. Facebook recently launched its own Facebook messenger chatbot called Assistant M, as well as a open source developer toolkit for bots.
You can already find AI chatbots in nearly every industry – from sales to customer support, consumers are seeing tangible improvements to user experience, fueling the surge in this tech revolution. As a branded Facebook Messenger bot, Hyatt customers can get up to date information in seconds. Using your customer's' previous purchases and support questions, these sales-minded AI chatbots deliver personalized product recommendations that consumers are most likely to purchase. In the second installment of our series on AI-based predictive analytics, we look at 5 brands using predictive analytics to improve growth and performance.
Facebook's intelligent assistant M is now available for Facebook Messenger users in Australia, Canada, South Africa, and the U.K. M in Facebook Messenger first became available in April. Tell someone good night and M may suggest a good night sticker. Facebook's AI assistant M first entered the public imagination in 2015 when private beta trials began for a personal assistant to help Messenger users with daily tasks or make restaurant reservations, buy a gift, or book a vacation. M and other AI produced by Facebook researchers could more than likely play a role beyond Facebook Messenger someday soon.
The AI powered bot shares fun sticker suggestions for your daily life interactions like'Thank you' or'Bye-bye.' The AI powered bot shares fun sticker suggestions (right) for your daily life interactions like'Thank you' or'Bye-bye' M is capable of recognising intent in a conversation, which allows it to perform a range of different tasks. The AI powered bot shares fun sticker suggestions for your daily life interactions like'Thank you' or'Bye-bye.' M also also allows you to save content from chats (left), including URLs, videos, Facebook posts, events, and pages.
OKCupid has banned white nationalist Christopher Cantwell from the dating service. And it's asking its members to report other OKCupid members who belong to hate groups. OKCupid joins a growing corporate backlash against neo-Nazis in the U.S. after the deadly white supremacist rally in Charlottesville, Va. Technology companies that once tolerated white supremacists are now booting them from their services. While tech companies have removed accounts belonging to the Islamic State and other terrorist groups under growing political pressure, tech companies until now have not been as aggressive in policing hate groups in the U.S.
The search and Android giant has acquired AIMatter, a startup founded in Belarus that has built both a neural network-based AI platform and SDK to detect and process images quickly on mobile devices, and a photo and video editing app that has served as a proof-of-concept of the tech called Fabby. AIMatter had people working in Minsk, the Bay Area, and Zurich (Switzerland being particularly strong in computer vision tech, see here, here, and here). This isn't just for fun apps that let you add dog ears and crazy hair colors to your photos -- although, as Fabby, Prisma, Snapchat, Facebook and countless others have proven, filters can be a lot of fun. But there are also Google's efforts in VR and AR; and its work in building machine learning platforms like TensorFlow for developers to build their own apps using machine learning (AIMatter's SDK could be notable here).
Fandango's Facebook Messenger bot lets you watch movie trailers, find local theaters, and see what's trending this week. Spotify's Facebook Messenger bot makes it easy for its customers to search for, listen to, and share music. Mastercard's Facebook Messenger bot makes it easy for customers to check on account transactions (e.g., just ask "how much did I spent on restaurants in May?"). Staples' Facebook Messenger bot can answer common customer questions, which tend to be about orders -- tracking and returns -- and whether specific items are in stock.
The world's biggest search engine offers recommendations and suggestions based on previous user searches. In 2012, Google introduced Knowledge Graph – an algorithm used to decipher the semantic content of a search query. Lyst is an ecommerce fashion site working with a new breed of model – the machine learning model. To match customer searches with relevant recommendations, Lyst uses meta-data tags to make visual comparisons between items of clothing.
The next level will be using artificial intelligence in election campaigns and political life. This highly sophisticated micro-targeting operation relied on big data and machine learning to influence people's emotions. Typically disguised as ordinary human accounts, bots spread misinformation and contribute to an acrimonious political climate on sites like Twitter and Facebook. For example, if a person is interested in environment policy, an AI targeting tool could be used to help them find out what each party has to say about the environment.
In other words, as things like style guides, design systems and pattern libraries become more important than the visual layout of individual pages, we're seeing a seismic shift in what web design actually involves. AI has already worked its way into mainstream web design, through technologies like conversational interfaces (chatbots). Meanwhile if you want to learn more about creating your own chatbot, check out our How to build a chatbot interface post, How to design a chatbot experience tips and these 5 essential chatbot learning resources. To improve your understanding of the use of words in UX, take a look at Guy Ligertwood's checklist UX Writing and How to Do it, and Making Chatbots Talk – Writing Conversational UI Scripts Step by Step by Anna Kulawik, and How to Write For a Bot by Paul Boutin.