A New Communication Paradigm for Humans and Bots
(This is a re-post of our TechCrunch article co-authored with Guoguo, Kenji, and Daniel Li, with information on Skype added)
Chatbots offer the promise of frictionless access to goods, services and information, but creating effective bots can be extremely tricky.
Giving users the opportunity to interact in a seamless, natural way has the flip side that user expectations can be prohibitively high. Bots need to be smart and provide greater convenience than apps, which are a very effective UI paradigm tailored for today’s mobile devices that has been carefully refined for more than a decade.
The good news is that there’s no reason bots must master human language or replace apps in order to succeed. Bots will engage with consumers in new ways that combine the strengths of humans and machines to power a natural and efficient exchange of both structured and unstructured information.
One simple but intuitive way to measure the effectiveness of communication is to look at the amount of information exchanged per unit of time. Using this benchmark, there’s a stark difference between interactions via text (e.g. SMS, chat, email) and via speech (e.g. phone calls) when it comes to the amount of information that can be produced vs. consumed.
While humans typically produce 120 to 140 words per minute when speaking, they can typically only write or type 40 to 70 words per minute. When we look at the speed of information consumption, the reading speed in English is upwards of 200 words per minute, while the listening speed is limited to the 120 to 140 words per minute.
SMS and chat apps have adapted accordingly to increase text production speed through autocorrect features and novel keyboards, but humans will always be laggards when it comes to producing compared to consuming text.
Imagine, however, a friend that can type, draw, look up information and find GIFs at superhuman speed, and produce buttons, menus and pictures to make your input faster. Better yet, your enhanced input is much easier for your friend to understand and does not take away the flexibility and familiarity of natural language when needed.
We may not be there yet, but we are very close, especially with well-constructed bots on certain platforms. Here is a look at the features of different bot platforms that are shaping human-bot communication toward a more efficient, robust and natural UI paradigm.
Quick Reply Buttons
Quick reply buttons are a simple and convenient way to save user time and prevent unexpected input. They are unique to human-bot communication as buttons are trivial for bots to create and easy for humans to use; benefits include enhanced communication speed and bot comprehension.
Facebook, Telegram, Kik and Skype bots all have quick reply buttons, but under slightly different names, and some bots, such as the Sephora bot on Kik, use the quick reply button as the primary mode of communication. Slack still lacks quick reply buttons, but has message buttons with associated actions.
Telegram Custom Keyboard:
Facebook Messenger Quick-Replies:
Kik Suggested Response Keyboard:
Skype buttons in a card:
Callback buttons are similar to quick reply buttons but afford a broader range of potential interactions. When a user clicks a callback button, it generates an HTTP call to a registered webhook that triggers a predefined action. Callback buttons are a great way to provide feedback, and they also provide a deeper analytics opportunity for the bot’s backend.
Slack Message Buttons:
Messenger Postback Button:
Telegram Callback Buttons:
Structured Information Sharing
Sharing information that’s easy to programmatically parse can take the exchange of structured information a crucial step further, from a clunky interaction in a language-only paradigm to a simple and unambiguous exchange in a hybrid setting.
For instance, sharing a location like “Third & Madison” is ambiguous and slow for humans and machines to parse, while shared GPS coordinates are easy to display for a map service and equally easy to understand by bots.
Telegram SendContact und SendLocation:
Facebook Messenger location sharing:
In-line bots are a great way to quickly obtain, send and share information during chats, without the need to jump out of the current interface (to go to another chat) or the current app (to go to another app).
Instead of multiple taps and menus to perform a specific function, an @mention for a bot provides single-line interaction. Allowing bots to share conversational context with one another also greatly increases the speed of interaction because users no longer need to re-enter data for each step of a conversation.
Telegram Inline Bot:
Slack Bot Mention:
Skype Bot Mention in Groups:
The following table summarizes the added language-touch functionality provided by five popular chat and bot platforms. These features represent the beginning of a hybrid communication paradigm that will enable more efficient and effective communication with bots:
- Quick reply buttons: save user time and improve machine comprehension
- Callback buttons: provide calls to action and back-end analytics
- Structured info sharing: easily share machine-readable information
- Bot mention: make bots always present and easily accessible
If your bot doesn’t use a language-touch hybrid communication pattern, there are several other ways you can still take some of the UI mechanics from buttons and callbacks to build a better bot:
- Build your system starting with humans in the loop so they can help you identify the most common communication patterns and exceptions.
- Optimize dialogue for two-channel — fast and slow — communication with clear, well-defined responses (e.g., “Reply YES to buy”) or open-ended messages (“Can you tell me when the new Taylor Swift record comes out?”)
- Use callback functions, even without native integration. For more complicated tasks, take users out of chat and move them to a point-and-click or touch interface that’s better suited to the task at hand.
- Consider moving to a platform that’s better optimized for new forms of human-machine interaction.
AI and NLP have a long way to go before bots achieve quasi-human communication skills. Before that happens, new methods of human-machine communication will take advantage of the strengths of both humans and machines to create new interaction patterns that come across as natural as our own language.