May 10, 2021
6 Minute Read
Tribe Dynamics launched in 2012 to help countless leading global brands operationalize, scale, and measure their internal influencer programs—all in a single influencer marketing software platform. Since 2017, the Sama team has powered this technology, training Tribe’s machine learning algorithm and increasing reporting capabilities by 350% to date, helping to build robust influencer communities for a fast-growing, global portfolio of brands.
While influencer marketing isn’t a new concept, it has become wildly popular in the past few years. It’s a type of marketing that uses endorsements and product mentions from influencers—tastemakers who have a dedicated social following and are viewed as experts within their niche. Influencer marketing works because of the high amount of trust that influencers have built up with their following. Recommendations from influencers also serve as a form of social proof to a brand’s potential customers.
But how do you measure who talks about you and how you compare against competitors?
This is where Tribe Dynamics comes in. The universe of what they track consists of two parts. First, a growing database of over 2,500 brands, including social handles and colloquial ways of discussing the different brands. You can imagine brands missing out on key conversations if they fail to capture slang or abbreviations like #ABH, referring to the popular cosmetics company Anastasia Beverly Hills. The second part involves the influencers who live in their ambassador relationship management system. Here, the profiles and online activities of 200,000 influencers are stored and sorted by the various industries and interests. When combining this list of brands with the group of influencers, Tribe delivers a powerful collection of social posts mentioning your brand—one that truly identifies your most passionate influencer community.
Tribe Dynamics’ direct users are marketing teams tasked with measuring the ROI of their influencer program. They want to track their share of the conversation versus their market share benchmark to assess how well they’re doing against competitors and identify their most effective influencers. In short, they need Tribe Dynamics to help them cut through the noise and make data-driven decisions.
Here’s an example; if a post is talking about Benefit Cosmetics and the company is tagged as such, it’s typically an easy find. However, it becomes more complicated when the algorithm needs to detect the difference between “I love this blush from Benefit” and “The benefit of using blush,” where one is a brand mention and the other a tutorial.
Marketing teams also need to be able to judge the quality of an influencer’s performance and avoid spending budget on fraudulent influencers. Tribe Dynamics allows them to see who their top drivers are for Earned Media Value (EMV), a proprietary metric that measures the value of third-party digital content created about a brand, and surface the right influencers. After all, the hardest working influencers may be people they don’t even know about yet.
Tribe Dynamics’ machine learning algorithm catches 95% of the mentions for some brands and 60% for others, and the team relies on Sama as part of their ecosystem to deliver full accuracy.
Sama’s expert annotators assume the tasks of locating, extracting, and tagging key brand mentions in the posts generated by Tribe Dynamics. This human-in-the-loop intervention consistently reaches a quality SLA of >99%, enabling the algorithm to become more intelligent over time.
Sama handles 60-70% of the monthly vetting tasks: identifying brand mentions and common language ways of talking about a brand that the algorithm isn’t yet trained on.
This continuous vetting also helps overcome model drift. In the fast-moving world of social media, training a machine learning model is not a single, finite stage in the process. Even after it’s deployed in a production environment, this steady stream of new training data—and continuous vetting—ensures the model’s predictive accuracy over time.
Its success shows in the numbers:
The volume of data Tribe Dynamics is able to provide their clients has grown almost 4x—from 700 brands in 2018 to 2,600 brands this year.
Sama has been key to this growth.
As almost all of the expansion involves vetting, Sama has been a valuable resource in Tribe’s international expansion.
“We’ve launched in over a dozen markets in two to three years. That, without support, would’ve crushed our internal teams. Sama was able to take on additional workload quickly and efficiently. It has been a notable piece of our successful global business,” says Clare Bruzek, VP of Operations.
Sama has become part of the architecture of the company. When Tribe Dynamics decides to expand into different markets, Sama is integral in the scoping of these new opportunities. “It’s the only sustainable vetting option for our international expansion. We now provide international data on 1,250 brands to 94 clients across 12 global markets, making up 30% of our revenue.”
“Working with Sama has made a demonstrable impact in our ability not only to service our current clients better, but also to expand our services to new types of clients and new markets. We have only been able to meet client needs in that way because of what Sama has been able to achieve.”
Amanda is the Content Marketing Manager at Sama, where each day she gets to learn about AI and how it’s transforming industry. She’s passionate about technology but periodically tries to get away from her computer to explore more analog things like collage and quilting.