Making Tina Talk

What our first chatbot taught us about language, machine learning, and listening to our audience.

rehab
rehab
Nov 7, 2016 · 8 min read

Writing

Very early in the creation process we concluded that Tina should really be considered a Q&A bot, not a chatbot. She can answer questions, but won’t keep a human-like conversation going. This is largely a limitation of the time and software that was available to us; it turns out that it’s surprisingly hard to retain the context that a natural conversation requires.

Training

Writing a bot is quite different from writing an application. It requires ongoing training, testing and tweaking, so we developed a process of iterative writing and feedback that gave us the best results.

Natural language services

The software we used to create Tina’s smarts is based on entity extraction — essentially, you look for keywords in a sentence, and use those to judge the intent of the sentence. So given the question, “how fast could you run?” we might say that the two important words are fast and run, and that they show that the writer’s intent is to know Tina’s maximum speed.

  • I lived in North America, 65 million years ago
  • I lived in North America, 65 million years ago
  • It’s possible we hunted in packs
  • What is the extinct?

Keeping the conversation moving

The moment your bot introduces itself is the first and most important opportunity to set user expectations. For example, the first version of Tina, would invite users to “ask me anything”, and… well, they did.

  • Who would win a fight between a badger and a gibbon?
  • Sorry, I don’t understand your question.
  • What did you look like?
  • So what is?
  • Sorry, that’s not my area of expertise.
  • Cool!
  • Sorry, I don’t understand your question.
  • Yeah, not bad.
  • Sorry, I don’t understand your question.
  • I’m not sure. I’m still learning, and every question you ask helps me. Why not ask how old I am?

The real audience

After training the bot with Mechanical Turk questions, we needed to get Tina into the hands of our real audience: children. We asked all the parents in the studio to test Tina with their children, and give us the results. We were pleasantly surprised with the outcome, as many of the common questions were successfully answered. But there were two question subjects we saw repeated frequently: Jurassic Park, and poo.

In the wild

We were now ready for launch. Tina went live in July 2016, and as we shared it out on our social channels we started to see conversation sessions begin. Many of the initial users were curious adults, and one thing we learned quickly was that they were keen to test Tina on current affairs:

  • Sorry, I don’t understand your question.
  • Let’s keep things clean.
  • Let’s keep things clean.
  • Say that one more time and we’re done here. I’m LEAVING.
  • What else can I tell you?
  • Were you dropped as a child?

Results

Tina was supposed to live on Nat Geo Kids’ Facebook page for a few weeks, but has been a great success and is still live there to date, with more than 15,000 chat sessions under her belt. We’ve had wonderful feedback from the press, including Fast Company’s statement that Tina is “the first truly awesome chatbot”.

Written by Peter Gasston

Peter is our Senior Creative Technologist at +rehabstudio. He has 15 years experience working on the web, is the author of two books, supports Arsenal and likes going on day trips to castles.

rehab

a creative technology company

rehab

Written by

rehab

Helping brands create scalable, one-to-one relationships with people through tech they love. rehabagency.ai

rehab

rehab

a creative technology company