Give your chatbot some real personality


Chatbots are all the rage at the moment.

These clever computer programs (algorithms, to be more precise) are popping up everywhere online to help you with mundane tasks from getting a weather forecast or currency exchange rate to travel planning to online shopping.

Organizations everywhere are experimenting with these useful bits of technology, with varying degrees of success as part of the learning process (remember what happened to Microsoft’s Tay earlier this year?).

If you use Siri on your iPhone, Cortana on a Windows 10 device, or say “Okay Google” on your Android device, arguably you’re using a chatbot. For the first two, Apple and Microsoft respectively sometimes describe these tools as “personal digital assistants” (PDA: there’s a déjà vu acronym) or “intelligent personal assistants.” Personally, I prefer IBM’s more precise descriptor of “cognitive personal assistant” although such a term embraces technology at a much greater scale and depth than chatbots.

There’s a weekly email newsletter about developments with chatbots, and there’s even an online magazine about chatbots.

So you’re certainly not starved for news, information and opinion about chatbots, whether in the mainstream or in the workplace.

A story in the Financial Times about chatbots  caught my attention for a couple of reasons. First, the sub-heading: “Prepare to be frustrated by AI programs that are designed to help.” And secondly, using the AI acronym for “artificial intelligence” in relation to chatbots.

The FT predicts that rather than going to a website to find information or downloading yet another app, we will summon these artificial intelligence assistants to do our bidding.

Bark “find me a flight to Chicago on Saturday” into your phone and a “bot”, which understands your location and the fact that you mean this Saturday, will return with some choices.

And adds:

Chatbots will become the predominant way we interact with companies. Apple’s Siri, Microsoft’s Cortana, Google Now, Amazon’s Alexa and Facebook’s Messenger are among prominent examples.

Chatbots are already evolving from their current embryonic and simple states of speaking at your phone; and we will see this evolution in varying stages and levels, and at varying speeds.

The FT highlights an example in the case of accountancy software company Sage which is planning to launch a chatbot this summer to help freelancers and small business owners manage invoices and expenses.

And here’s what’s interesting about this:

Kriti Sharma, who built the bot for Sage, says one of the challenges has been ensuring that it is not annoying. She has spent considerable time thinking about how the bot should react in different situations. Swear at it and the Sage bot responds with a sad face emoji and says “I’d rather talk about accounting”. Tell the bot you love it and it says you have excellent taste before gently steering you back to accounting.

Imagine the scale of the keyword recognition list!

The FT’s report touches on personalities, citing Clippy – the animated paper clip that used to pop up on Microsoft programs when you were trying to type something – as a worse-case example, noting:

The difference between Clippy and today’s chatbots is the arrival of deep learning, which makes computers capable of a far more complex level of pattern recognition and allows them to follow natural language and speech better.

And that leads to an idea whose time may have come as Kriti Sharma explains:

“We are very careful about the frequency with which the bot responds, and we have built the personality over time,” says Ms Sharma. “I now need to hire someone to take this further – a bot personality trainer.” Such a person might be a creative writer rather than a technical specialist, she says.

Among the wider debate that new-technology in the shape of AI is going to replace people in the workplace, add this aspect to that debate – opportunities will present themselves for you to re-imagine your role and pivot in a new direction. And think about ethics and the real dilemmas confronting us as AI becomes more pervasive.

For creative communicators, this could be a great place to start.

(Image at top of C-3PO via Build2Master blog)

Neville Hobson

Social Strategist, Communicator, Writer, and Podcaster with a curiosity for tech and how people use it. Believer in an Internet for everyone. Early adopter (and leaver) and experimenter with social media. Occasional test pilot of shiny new objects. Avid tea drinker.

  1. Ronna

    Hi Neville, I recently contributed on a ‘crowd sourcing’ platform to ideas for a major international bank around artificial intelligence and digital transformation. Lots of the ideas from other participants included bots, and virtually all of the imagery was ‘robotic.’ While many of the underpinning ideas were great, I agree with you that constant use of this kind of imagery is unimaginative in the least, and missing the point at worst. I’d love to see companies embracing the imagery of the problems AI and bots are now helping to solve as part of an overall business approach, and relating to what is truly valued by customers. Not lots of little animated robots which to me are pretty meaningless, as the automation/robotics speaks to efficiency savings (for the company and perhaps its partners) and not the value add (to the customers). And as there are only so many ways to draw a robot, it is hardly distinctive and differentiating! When I expressed this thought on the platform, a younger male participant ‘mansplained’ to me how bots are the future, refusing to believe that there was more appropriate, and potentially less intimidating (to some) imagery. Regards, Ronna

Comments are closed.