Editor’s note: Yasha Spong has worked in the media fingerprinting space since 2008. Prior to joining Zample, he was at Audible Magic and Getty Images.
Brands are spending large amounts of money on sponsorships, in particular in sports, which are seen as a unique way of engaging emotionally with fans. Ideally the brand will be featured prominently in an image of a star player scoring a key goal for the home side and reap the benefits of being connected to a moment of collective glory.
Anecdotally brands get “a lot” of exposure for their sponsorships of teams and athletes via images shared on social media, but up till now, no one has been able to quantify this valuable audience.
Luckily for brands, the convergence of existing computer vision technology and the recent advances in machine learning are changing the game. Large-scale analysis of social media images to identify brand logos and gather useful information about audience and engagement is now emerging as a credible approach to earned media measurement, especially for sport sponsorship. It is now possible to look inside the image to detect faces, objects and brand logos at a scale, speed and accuracy that was impossible a few years ago. These new approaches reveal huge audiences and high levels of engagement that were previously invisible.
Tech giants are getting serious about the space. Google’s object recognition effort and Facebook’s DeepFace initiative are adding these capabilities to commercial services right now. Advances in image analysis are likely to continue as labs like the Berkeley Computer Vision Group are churning out new grads versed in these cutting-edge approaches.
Visual measurement isn’t just for the big guys or the academics. The new services available from companies such as like Ditto, Kuznech and Blinkfire, combined with inexpensive cloud computing puts brand-spotting within reach for brand managers.
For example, below are measures of the incidence and reach on Twitter of the Qatar Airways sponsorship of FC Barcelona during their game against Real Madrid on March 22. The images were gathered from Twitter selected by hashtag, location and time. This example did not select specific influencer accounts or run any general text searches. Rather the results are of general visual identification of the Qatar Air logo as it relates to FC Barcelona and the Twitter audience interested in this particular match.
In this small sample, we processed 55,534 tweets. Of those tweets, 4907 contained images. Of those, the Qatar Air logo was detected in 480 unique images.
These 480 images in turn generated 6,540 favorites and 8,220 retweets. Summing the followers of these tweets and the total impressions generated for the Qatar Air brand is an astounding 60 million. On one night.
Until now, neither the brand nor the club or anyone else in the ecosystem of sport sponsorship has been aware of these numbers. Football sponsorship alone is worth billions of dollars each year. The way that sponsorships are marketed and purchased is about to change forever.
Keys to engagement
Now that we have brought this hidden earned media data to light, what can we learn about how the social audience is engaging with content that contains our brands? What themes are grabbing user attention and how can brands join the conversation that they are sponsoring?
To switch gears from Spain to the UK, a general analysis of tweets containing sponsor logos in the English Premier League this season shows four main themes.
In order of engagement (as measured by retweets and favorites) the top themes for tweets with images showing brand sponsor logos in the EPL are:
- Stats on players and teams – usually posted just prior to or just after a match
- Game action – most often posted by the club themselves
- Match info – dates, rosters, schedules of upcoming matches
- Player personalities – fans love a birthday note to a favorite player
Moneyball for earned media measurement
Players in the sport-sponsorship market worldwide, such as Ogilvy, are starting to pay attention to the potential of this new kind of brand measurement and how to leverage this technology to bring quantitative analysis to the social media aspect of earned media measurement.
This trove of quantitative data on the visual conversation that includes their logo also suggests concrete actions that brands can take to join the conversation around the events they sponsor.
For example, once a compelling image is surfaced brands can:
- Retweet, favorite, comment directly in the conversation. As long as this is done “as a fan”, it doesn’t “commercialize” the conversation, but strengthens the emotional connection between the brand, team and audience.
- Identify influencers who are already sharing branded content and create a direct relationship. Large and highly engaged audiences can be found already consuming branded content; there is room for brands to grow this relationship.
- Be a cheerleader. Fans already accept the brand as a sponsor. They have an emotional connection to the team. On some level, the brand sponsor has already paid for the opportunity to be a part of that emotional connection. Brands are missing a huge opportunity by not being an active cheerleader in social media, especially open platforms such as Twitter.
And the winner is….
Widespread adoption of these new technologies will change the way earned media is measured. Brands will have new ways to measure the ROI of their sponsorship dollars and engage directly with the audience that is already emotionally connected to their brand. Brands, agencies, teams and events that grasp these tools now will lead in the future.