CHALLENGE
For Sprite’s #ILOVEYOUHATER campaign, our objectives were three-fold: increase brand awareness and boost transactions, become a badge brand for GenZ by being relevant, and create a one-of-a-kind experience while also reinforcing Sprite's product intrinsic qualities:

1. Transparency (owning who you are)

2. Refreshment (acting spontaneously and creatively)

3. Lemon-lime acidity (witty humor & touch of irony)

INSIGHT
We wanted to become a badge brand for GenZ so we needed a way to involve ourselves in one of their most hot button issues: online bulling. In order to be relevant we knew that we needed it to be as real as possible.

Using Twitter data, we developed and trained a custom machine-learning algorithm that helped lead us to the protagonist of our story, our hater: @AguanteElCofler.

SOLUTION
Via the Twitter API, we downloaded 15,000 tweets from Argentines notorious for being bullies or being bullied. Their conversations, along with a proprietary dictionary of Argentine Spanish words and phrases that helped us navigate a complex jargon and decipher the connotation of each tweet, trained our machine-learning model.

Once the training was completed, we had it process more than five million tweets from over 100,000 unique users from Sprite ́s Twitter community and other brand ́s accounts with a high affinity to Sprite ́s teen target. Classifying each tweet as offensive or non-offensive and differentiating the haters from the non-haters.

To better understand our audience and the current context of bullying in Argentina, we used natural language processing techniques to identify the over-arching themes used by haters to assault their victims: Ideology, Body Shaming, Trolling, Gender Warring, and Identity.  

Finally, we generated a scoring, which brought us to our hater: @AguanteElCofler.