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.
The top ten: Amazement, Anticipation, Generosity, Indulgence, Excitement, Happiness, Joy, Love, Good cheer, Reflection.
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.
We then found the top 10 beers that matched one of our New Year emotions: Joy, Harmony, Resolution, Optimism etc. An analysis of all their recipes to find the most common ingredients gave us the recipe for our new year beer.
The final result was that a beer that tastes like New Year optimism: should contain Honey, Nelson Sauvin and Hallertauer: Honey for love and cheerfulness - Nelson Sauvin for optimism, imagination and resolution - and Hallertauer for excitement and emotion.
Our beer was brewed in partnership with an expert independent micro-brewery in the Peak District, High Peak Brew Co. We chose to work with them because their brews are unfined and unfiltered which meant we got the closest taste to the data we could get.
The result is a fine tasting cream ale in a limited edition of 500 bottles.
So what does 2016 taste like?
Optimism. Love. Imagination. Add gentle overtones of excitement, with light notes of intellect, and you’re drinking-in the year ahead.
If you’d like crack open a bottle for yourself, drop us a line and share our story: