Case study – Keyword List Building Guide – Negative Hype Media

Case study - Keyword List Building Guide

Im gonna walk through the keyword list methodology, in this case using Alexa.

The keyword lists we are talking in reference to are the keywords you bid from within a pay per click ads platform. A bulk amount of relevant keywords with very low bids can produce low cost trickle down clicks scattered from across the multitude of keywords you bid on. This can be adapted to a wide scale of strategy, and differs between search engines and platforms.

As this image shows, I found about 6,000 music relevant keywords specific to Youtube and downloaded the list:

Note how when I do the breakdowns, I do so on the ad set level since we have too little spend to put any consideration into the individual ads yet. It’s probably too little spend for even just the global ad set data so I upped the budget to $10/day. As you can see the drop off from 3 second views to 95% views is immense, as expected. Facebook user’s video engagement habits tend to heavily favor shorter ads, and some users my have their settings not to play sound initially on videos. This kills the goal for musicians obviously.

Here you can see the list and statistics provided by Alexa in a spreadsheet:

 

So I trimmed out some of the very low popularity keywords:

Then using my program of choice for this sort of thing, Scrapebox, I remove keywords with too many characters and those that contain illegal characters according to Adwords standards:

I uploaded the list into the Adwords campaigns, both of them:

I also added them into the bing campaign as well.

Here are the two A/B ads as a general overview:

Here is some segmented data from the ads performance today before integrating this new keyword list:

If anyone wants me to export and share any specific keyword reports from Alexa including the one I used, let me know, I’d be glad to accomodate. I’ll share my results as I come across anything interesting with any of these campaigns. Feel free to ask questions I’ll answer everything I can.

The keywords dataset I built for this study is available Here. You can view/filter/download it, in its entirety for free, no need to sign up or opt in to anything to do so, I just wanted to make it available in a user friendly format. Let me know if you’d like me to provide anything else.