endeavor logo

  • JUser: :_load: Unable to load user with ID: 45
Thursday, 15 December 2016 10:39

Endeavor company BrandsEye proves the power of social media analytics, the human voice

endevor image jp kloppersJust a few months on from accurately predicting the Brexit vote, BrandsEye has once again proven the power of social media through its analysis of the US elections, which pointed to a Trump victory.

Social conversations amongst US citizens were sent to the BrandsEye Crowd – its crowdsourcing platform that assigns microtasks to trained contributors around the world to correctly allocate sentiment to the candidates (for or against) in return for micropayments. BrandsEye’s weighted average matched the outcome of 9 of the 11 states, proving the accuracy of social media analytics compared to more traditional methods of analysing data.

According to a release published on BrandsEye’s website, entitled How BrandsEye analysed the US Elections, which explains this in more detail, BrandsEye believes that ‘nuanced and accurate interpretation of online sentiment is now vital if businesses, organisations and institutions want to really understand the voice of the people, not just what we might wish it to be’.

Here, JP Kloppers, CEO of BrandsEye, explains how it went from being a well-known media intelligence company to the global leader in sentiment analytics, virtually overnight.

Are you starting to see a shift from traditional polling to adopting more modern methods such as sentiment-driven analytics?

Not yet, but on the back of us calling both Brexit and US elections using sentiment driven social data, I think the world has finally woken up to the value of accurate social media data. Although there is still a place for traditional polling, social media does carry a lot of complementary benefits. To start with, the scale of the conversation being monitored is far larger than traditional methods, which means you get to listen to a lot more opinions from a lot more people across various demographics.

In the case of the US elections, we were looking at over 37 million conversations from over 4 million authors over a four-month period, which allowed us to accurately gauge the shift in social sentiment towards Trump.

Another benefit of social media is that it allows for real-time opinion analysis that is generally not influenced by external factors, such as an interviewer. Authors are generally also a lot more open and honest when sharing opinions. This is extremely valuable, especially when looking at the underlying reasons driving the expressed emotions.

It is very important when talking social analytics to differentiate between two approaches. The first, the pure algorithm one uses an algorithm only to analyse large sets of data. The second, the crowd approach combines human understanding with advanced technology. Through the crowd approach data is put through our team of human raters who analyse it for sentiment, relevance and topics. This data is then fed back into the algorithm so it can learn and adapt.

When looking at something as complex as the US elections, or Brexit, the ‘crowd’ is a critical component as it is able to correctly attribute mentions with sarcasm, implied and hidden meanings, abbreviated phrases, swearing and innuendo – all of which are common practice in social media. When it comes to these social complexities, even the worlds most advanced artificial intelligence (AI) struggles to correctly attribute sentiment.

As the world becomes more connected, differences between decision makers and their stakeholders are becoming more visible and volatile than ever. Traditional methods of understanding a broad group of people are breaking down because they can neither measure the intensity nor the commitment of the emotions. Sophisticated analysis of social media, however, offers a more reliable understanding of what is really happening in today’s world.

Were these projects (measuring the Brexit vote and US elections) self-funded to prove the power of analysing social media data to understand human sentiment?

They were, yes. We took a strategic decision early in 2016 to stop talking about ourselves, and to simply use our technology to talk about things the world was interested in, and where broad-based sentiment insights would add value. Brexit and the US elections were two very public examples of this, and where the outcome was very obvious for everyone to see. Most of our work doesn’t have this dramatic outcome, but still points to the same underlying value proposition: measuring how people feel gives an indication of what they will do tomorrow. We are by no means a polling company, but we have a technological advantage that allows us to see clearly into this market too. Most of our clients use our software and sentiment analytics approach to better understand the sentiment driving consumer behaviour in their markets.

You crowdsource trained contributors to assign sentiment to the candidates in exchange for payment. How many jobs have you created in this way?

This year we’ve created about 40,000 hours of work for our crowd, or the equivalent of 50 full-time annual jobs. The BrandsEye crowd is potentially a massive job creator for unemployed or underemployed people around the world. We currently have thousands of people all over the world working for us and the number is growing daily. In a world being increasingly driven by automation, the integration of human understanding and intellect is critical to accurate social data, and is a perfect example of how technology can actually serve as a job creator, not a job destroyer.

Comment on the publicity you’ve received as a result, and how this is fast tracking the growth of the business.

We were able to do what no other polling, research, social media analytics, nor AI company in the world could do. BrandsEye therefore went from being a well-known media intelligence company to the global leader in sentiment analytics, virtually overnight. On the back of the US elections in particular we have had great traction from all over the world including Europe, the US, the Middle East and Asia with both potential clients and prospective investors wanting to know more about us. We’ve been featured on BBC, CNN, Reuters and Fortune to name a few.

What is the best advice you’ve received from an Endeavor mentor lately, and how have you applied it to your business (and these projects in particular, if relevant)?

It’s easy to get caught up in the early stages with raising funds, getting creative on corporate structures, and talking about strategy that is a few steps beyond where you are now. One of our mentors encouraged us to focus on building a solid business that creates value for your clients, and to then do that again and again. It was such simple advice, but helped focus our attention on the things that mattered most.

Comment on the potential impact media intelligence could have on the economy.

Media intelligence and, in particular, social media analytics, has the potential to raise the quality and competitiveness of companies on both a local and global stage. The ability to rapidly understand consumer emotion and experience means that brands, governments, agencies and organisations will be able to better position their products and services to meet customers’ needs. In the post-truth world, the ability to quickly and accurately understand consumer emotion is going to become a critical element in every single organisation that cares about their stakeholder and customer experience.

What’s next?

We’ve invested heavily over the past few years in building our technology and our crowdsourcing platform. The next step is to invest in our global sales and distribution channels. We’ve got about 16 verticals that we’ll roll out over the next 18 months, of which supporting the polling industry is only one. Our focus as a company is providing accurate social media data driven through sentiment analysis that organisations can use to make informed business decisions.

As a company, 2016 has been an amazing year for us and on the back of all our recent successes we’re looking forward to an even more successful 2017 with significant global expansion on the horizon.