A Beer Was Made With Social Media Posts
There's no question about it: craft beer establishments and homebrewers keep pushing the boundaries for beer recipes.
What would have been a novelty even a few years ago (mango habanero, grapefruit IPA, extreme sours) has become common, even pedestrian in some cases.
So, you've really got to think outside of the box if you're looking to stand out in 2016. Where did one English brewery decide to derive their latest recipe?
Marketing company Havas Helia, IBM's Watson, and High Peak Brewing in England all came together to make a beer from tweets. Seriously.
Our final beer recipe was defined by matching beer tasting notes with new years sentiments using data experts and IBM’s super-computer Watson.
We analysed the top ‘emotional’ keywords associated with the start of the New Year from social media. We then scored thousands of New Year related messages against a set of 24 pre-defined emotional states. These two steps gave us 38 separate emotions with a clear tie to New Year, ranging from optimism, excitement and resolutions to joy and dread.
Next, we fired up Watson Alchemy and analysed 2800 beer recipes, pulling out the frequency of ingredients, their recipes and tasting notes – and how people reviewed the beers. We used Watson Personality Insights to analyse each recipe and characterise it according the values, needs and emotional states – essentially profiling each beer as assertive, friendly, intelligent, etc.
Mmmmm... I taste a slight hoppy profile with notes of self-importance, groupthink, and hashtags.