A Slice of TADSummit: Conversation Intelligence

In this blog we focus on the presentations given on Conversation Intelligence at TADSummit Asia 2021 through May. Thank you to Neeraj Choudhary, Symbl.ai; Muzzamel Mazidee, UIB; Elayne Ruane, LERO Centre; Dr. Shona D’Arcy, CEO Kids Speech Labs; Ruwan Dissanayaka and Thushara Rankothge, Extrogene Software for all your excellent contributions.

Here are the presentations, and below we review them and their importance to the programmable communications industry. Click on the titles to go to the weblog for the video, slides, outline, review and Q&A.

Conversation Intelligence for Developers

Symb.ai is an API platform to analyze voice, text, and video conversations in real-time using artificial intelligence and machine learning. You don’t need to build any machine learning models. Symbl.ai can contextually understand conversations for your applications. The platform will also work on pre-recorded content (async), not just real-time conversations.

They’re also a sponsor of TADHack Global 2021 in September, more coming on that very soon.

The contextual understanding of a conversation is a significant acceleration for developers as training a model requires gathering data, cleaning it so the data trains the model accurately. With Symbl.ai you can skip this step, which for a hackathon is really handy 🙂

Neeraj walks through how you can quickly get up and running with a great demo using their ‘symbl-twilio-video-react’ repo on their github page. A video application that uses Symbl APIs, built with Twilio video SDK and React.js

I particularly appreciate the explanation on initial set-up as often those first couple of hurdles, though straight-forward once you’ve done it once, can catch you out. Yes, I know, read the documentation, but who does 😉

You can get in contact on Twitter SymblDev or Neeraj.

How Not To Build a Chatbot

One of TADSummit’s policies is “no BS,” and this presentation is a great example of just that. While many presentations hype chatbots as the greatest customer service innovation ever, it simply does not jive with our everyday experience. Mel’s presentation lifts the lid on why that’s the case and helps us understand the steps towards success with chatbots.

When Mel runs through what bot implementations get wrong, this is spot-on and excellent insight:

  • Users’ needs. If the bot cannot help the customer get to want they want faster / easier than what you’re doing today. Don’t do it, as it will frustrate the customer. If you’re going to send your customers to watch a video for 10 minutes, make sure this will resolve their problem. After 10 minutes and an unresolved problem, the customer is now furious at your brand/business for wasting their time.
  • KPIs, tracking, and ROI. It takes time to fine-tune the bot to the specific application — test, test, test. Without metrics, the project cannot develop towards delivering business results and customer satisfaction.
  • Users’ favorite channels and preferred languages. I cannot overstate the importance of this. Asia is the most diverse region for channels and languages.
  • It’s “dumb.” The bot can’t handle multiple intents/languages.
  • It’s not used. Some of the initial HR and FAQ bots suffered from this as the user volumes were low and/or user benefits slight. If it doesn’t benefit the customer, they will not use it.

I love this quote he uses at the end, “One reason a chatbot takes more effort than either self-service or a human agent is that compared to us humans, it’s stupid.”

Pitfalls and potholes of content moderation for chatbots

Moderation is more than a social media chat room problem. Its an issue for any brand using a chatbot to engage with its customers and prospects. Google has a team dedicated to it within their AI Ethics.

Elayne works on bots, especially in customer service; abusive messages come with the territory, they are unavoidable. Even abuse directed at the people creating the bot. Its born out of customer frustration. A critical point Elayne makes is the decisions a brand makes around moderation have a significant impact of how customers perceive the brand and in protecting the user.

Elayne provides excellent advice on managing moderation:

  • Thoughtful design is important (legally, morally, commercially…)
  • Protecting the user is #1 – give users recourse and the benefit of the doubt
  • Your chatbot is just ones and zeros but your team are people!

Voice technology for Healthcare

This is an excellent introduction to the many uses of speech recognition in the Healthcare industry, which accounts for about half the voice technology investment.

Because voice requires neurological, cognitive, and physical capabilities its a powerful tool beyond the automation of taking notes, into improving accessibility to health services, and it can even be used diagnostically.

The final point on the role voice can play diagnostically is very interesting; across cognitive decline, Parkinson’s, cardiac arrest, depression, schizophrenia, and even COVID. I have noticed that people going into a depressive episode talk and interact differently, their face can even look different. It’s still early days in the application of speech technology diagnostically, its moving out of the lab into trials. There are so many exciting applications of speech recognition!

EVA from Sri Lanka

Ruwan and Thushara were one of the first TADHack Global winners, all the way back in 2014. From that success they’ve built Extrogene Software into an award-winning powerhouse of service creation, as described in their presentation.

EVA (Extrogene Virtual Assistant) is a chatbot creation platform focused on Facebook Messenger. Especially in the Middle East and Asia, SMS has become a distant second fiddle to WhatsApp, Facebook Messenger, LINE and WeChat when it comes to messaging.

EVA has a series of templates for common chatbot use cases, no coding is required. And you can customize the templates as well. Businesses large and small can now respond to customers and prospects quickly and accurately over social media.

I recommend you check out EVA in Motion and have a go in creating your own EVA, it’s easy and fun. Plus they have the analytics and dashboards you need to monitor and improve EVA for your specific applications.

One thought on “A Slice of TADSummit: Conversation Intelligence”

Leave a Reply

Your email address will not be published. Required fields are marked *