from Marketing Memetics, by Michael Taylor
Every experienced marketer can recall a time that tweaking just a few words of adcopy had an astounding impact on performance. Twain called the difference between the almost right word and the right word “the difference between the lightning bug and the lightning”. Adcopy is replicated and altered across multiple campaigns, performance by ad isn’t granular enough. Deconstruct ads into their component parts to find which words or phrases contribute the most to sales – as Burnett calls them “magic words” – so you don’t accidentally abandoning what’s working the next time you refresh your creative.
Split the ad text into individual words, then aggregate the data of all ads containing that word. Calculate common KPIs (Key Performance Indicators) to break down relative performance. Take this analysis one step further with NGrams – 1, 2, or 3+ word combinations appearing consecutively – to understand how words work together. The word ‘star’ may show a low ROI (Return on Investment), skewed downwards by ads for ‘2 star’ hotels, but ‘4 star’ might be a top performer. Edit out poor performers to eliminate wasted ad spend, and apply your best phrases liberally to dramatically improve performance.
It’s common practice to clean ‘stop words’ – common words like ‘the’, ‘is’, or ‘at’ that don’t add anything to the analysis – from the data first. Advanced techniques include lemmatization or stemming – grouping related words together – to make the analysis easier to interpret. These techniques are freely available open source NLP (Natural Language Processing) libraries such as NLTK, spaCy and Scikit-learn.
Name | Link | Type |
---|---|---|
AdWords Script: Find Your Best And Worst Search Queries Using N-Grams | Article | |
Best Python Libraries Of 2021 For Natural Language Processing | Blog | |
Lemmatisation | Reference | |
Measurement and the Magic of Message | Blog | |
n-gram | Reference | |
Stemming | Reference | |
Stop word | Reference |