Picture this. You’re at a Gourmerican burger joint chomping a cheeseburger, when an outspoken vegan friend starts preaching that you’re killing the planet. Last week, that same vegan downed a pricey glass of pinot before their flight to a far-flung destination, armed with their strongest mossie repellant and first aid kit. Anything amiss?
A new social media monitoring tool created at the University of Queensland is aiming to help marketing and PR professionals better track relevant stories related to their brand or area of interest as they unfold.
Hypermancer taps into unstructured big data, such as textual data from Twitter, and sorts relevant hashtags, mentions and keywords to classify and then present a user with different narratives and stories emerging around a situation or topic in real-time.
The tool is based on a dynamic model of human memory, called Schema Memory, which it uses to group conversations into contexts and story cards so users can see quickly what is most relevant to them.
As an example, if the search term is ‘oil’, and the user is searching on Twitter, Hypermancer will return options grouped as crude oil, hair oil and cooking oil. The user can then select which is most appropriate to see specific tweet threads and content.
Co-founder and creator of Hypermancer, Dr Andrew Smith, said the company is working to release three products based off the new technology: A consumer search tool; a placement product for targeting specific messages in social channels; and a professional tool, which will be available on a paid subscription model.
The consumer and placement products are due out in December, while the professional version of Hypermancer is expected to launch in the first quarter of 2015. The tool is being brought to market by Hypermancer SIA, which was spun out of the University of Queensland’s commercialisation arm, UniQuest.
Hypermancer has already attracted funding from Imprimatur Capital Fund Management for its launch, but will also look to raise further capital in the new year.
Dr Smith said the idea for Hypermancer stemmed from his work on text analytics over the past 14 years. The tool currently focuses on Twitter and news data, but can be applied to other social channels.
“It interested me that text contains many different world views – what we call ‘knowledge schemas’,” he told CMO.
“Social media has made that really obvious. Previously, when we used tools like customer surveys, it wasn’t as obvious and you could argue that customers were in general agreement, even if they weren’t.
“But there are so many different connections and views on important events, you need a system that acts like a prism, which can showcase the different colours of conversation.
“It answers the questions you should have asked.”
Dr Smith claimed Hypermancer will allow people to understand popular opinion about situations as they unfold. He suggested the tool could be useful for marketers looking for the right context to target messages or track brand sentiment, as well as PR practitioners, journalists and bloggers looking to identify, track and place content in the right conversations.
Dr Smith was also keen to see the tool used on a wider range of data sources such as digital media as a way of providing more accurate and relevant content search results. This could be a replacement for human tagging, which he pointed out was both labour intensive and not always comprehensive enough to recognise how a piece of content is relevant in another context.
“It’s like saying ‘show me what the situation is right now, who’s doing all the talking, and what do they really mean’,” he added.
Follow CMO on Twitter: @CMOAustralia, take part in the CMO Australia conversation on LinkedIn: CMO Australia, join us on Facebook: https://www.facebook.com/CMOAustralia, or check us out on Google+: google.com/+CmoAu