6 Principles of Designing Better Conversation
Voice User Interface should be the 2nd best thing that you should be worried about, 1st one would be humanizing the conversation with the user & a machine.
Why Voice User Interface (VUI)?
Let’s take an example of steps involved in setting an alarm.
Step 1: Take out your phone.
Step 2: Unlock your phone.
Step 3: Open menu (Yes, I am an android User).
Step 4: Browse through apps to find & open the Alarm app.
Step 5: Set hour.
Step 6: Set Minutes.
Step 7: Set AM/PM.
Step 8: Set the day.
That’s nearly 8 Steps just to set an alarm. These can easily be achieved by 1 step through VUI. Just say “Ok google !! Set an alarm for 5 am”.
VUI can’t solve all the manual processes but it does can solve many like setting your meeting, booking appointments, booking flights, Playing songs, Changing the lights of your room, etc.
Let’s take a step back, we will observe that there is one thing common between all the voice interfaces - We have to call their name (“Ok Google”, Alexa, etc). That does make sense. It’s like calling your friend in a crowd to get their attention. After that, there is an exchange of conversation happens.
Context: While working in Infosys Design Team, we got a chance to explore the VUI world. Our main task was “Leveraging Voice User Interface(VUI) for Dementia”. I had an awesome team. It was of 3 members including me, Kruthika Priya & Kushboo Rathod.
How to design a conversation between a user & a VUI?
Google has laid down 6 principles that we have to consider for designing better conversations with a VUI.
- Give your VUI a personal:
Compare these two calendar apps, the first with the assistant’s character, or “persona,” left to chance and the second with persona by design.
Studies have shown that we rely on speech to evaluate other people in terms of friendliness, honesty, trustworthiness, intelligence, level of education, punctuality, generosity, being romantic, being “privileged,” and suitability for employment. In short: speech is powerful!
Whenever you are planning to design a VUI (how it will sound!!), always think about the users who are going to use it.
2. Move the conversation forward
I hope most of you might have got a reply from your friends in one word.
For eg:
Rick: Hey!! How was your day?
Nina: Ok
Rick: Did you have your dinner?
Nina: No
Rick: Did you watch the new episodes of Naruto?
Nina: No
You can observe in the above conversation that it’s extremely disengaging. In everyday conversation, there are a lot of questions that seem to require yes or no answers. But they’re actually asking for much more information. Here are two examples:
Responding to “Can you play a song for me?” with a “yes” or “no” doesn’t meet conversational expectations. You’re probably wondering why these speakers seem so uncooperative. It’s because they’ve broken a core rule of conversation called the Maxim of Quantity. According to this principle of conversational behavior, a speaker provides the listener with as much information as is needed to advance the purpose of the interaction. So even if a speaker addresses the literal intent of a question, the interaction won’t feel satisfying unless they move the conversation forward informatively. In these examples, we never find out who all is coming to the party, nor do we hear a satisfactory reason for not being indulged with a tune.
But it’s not just the assistant who is socially intelligent enough to move the conversation forward — it’s also your users.
3. Be brief, be relevant
A smart VUI knows where to stop & take the conversation forward. Compare these two examples, the first VUI overwhelms the listener while the second is more concise:
In the 1st eg, VUI overwhelms users with too much information (high cognitive load) & while in the 2nd VUI remains brief and to-the-point, providing a more natural and pleasant interaction.
The speech signal is also linear, making irrelevant information especially irksome in VUIs, because unlike GUIs, there’s no way to skim over the material.
Keep messages short and relevant. Let users take their turn. Don’t go into heavy-handed details until or unless the user will clearly benefit.
4. Leverage context
A good conversational participant keeps track of the dialog, has a memory of previous turns and of previous interactions, and evidence awareness of the user’s circumstances. A well-known example that’s universally disliked is a VUI’s request to “Please listen carefully as our menu options have recently changed.” Here’s another version:
It assumes that the user has called before. It assumes the user who has called before heard a different design (different “options”) — that is, they didn’t call just a few minutes ago.
We talk a lot in this industry about personalization, artificial intelligence, and data-driven innovation. But designs that simply keep track of the conversation and remain “aware” of the user’s context will effectively advance the perception of human intelligence.
5. Direct the user’s focus through word order and stress
For VUI to act like a human, it has to remember the conversation & then reply back to the user by leveraging the context. Listen to these two examples of different VUIs responding to a user’s request to book a flight on a date that doesn’t exist:
Why does the first recording sound weird and robotic, while the second seems conversational? The explanation is the End-Focus Principle. As per this rule, “New” information by default comes at or near the end of the sentence and is stressed, while “old” information precedes it. In the examples you’ve just heard, what’s “new” is the info “30 days,” so it feels right at the end, and stressed appropriately. In the version that sounds strange, the old information, the topic “June,” has been miscast as if it were new information for the listener. In order to sound natural, it shouldn’t be stressed or come at the end of the sentence.
6. Don’t teach “commands” — speaking is intuitive
Machines are made for humans, humans aren’t made for machines. Machines should change their behavior w.r.t needs of human needs.
Avoid “teaching commands” in a VUI. If you have to explain a command, something’s wrong; go back to the drawing board. Instead of spoonfeeding commands, why not ask a question and make it clear the user can take their turn — sound familiar? That’s conversation!
These messages imply that you need to be taught how to use English; otherwise, the VUI wouldn’t be giving you these instructions. No one grew up knowing that “1” means “tech support”; we have no intuition about what meaning a developer or designer has assigned to the hash key. But in the world of VUI, this prompting style sounds absurd. It reveals a failure to understand that the whole point, the real benefit, of offering the public a VUI is that speech is intuitive; it doesn’t need to be taught.
You can read furthermore about it at the below link:
https://design.google/library/conversation-design-speaking-same-language/
Books:
Designing Voice User Interfaces: Principles of Conversational Experiences
by Cathy Pearl.
