'SEO' Archives



Commercial Intent Detection Tool Review

Saturday, May 10th, 2008

snap6.jpgAnyone who’s buying or selling advertising online doesn’t need a detailed explanation of why we want to be able to interpret whether a particular keyword phrase indicates an intention to make a purchase or not. We don’t just want traffic to our websites, we want traffic that converts.

While it’s sometimes fairly obvious - either from the words in the search phrase (where can I rent a beach house in Wildwood?) or from the detail within the search phrase (3 bedroom beach house in Wildwood with WiFi) - this is something that optimizers and pay per click campaigners struggle with continually. 

The Tool 

So, when MSN adCenter Labs unveiled their Commercial Intent Detection Tool about a year ago, it seemed like a great idea. Here’s what they say it does:

Predict a customer’s intention to buy, sell, or complete another kind of transactionbased on her search queries or recently visited URLs.

They backed the release up with an explanation entitled Algorithmic Commercial Intent Detection of Search Queries. The one-pager begins with:

Using algorithmic commercial intent detection, 52% of queries were determined to be associated with commercial intent. The alogorithm was deemed very accurate, with a rate of 90% for detecting both commercial and non-commercial intent.

The Research Behind the Tool  

Then, in the manner of content that appears to be scientific, it dryly goes on to explain why and how the algorithm testing was done. Human evaluators were used to check and verify the accuracy of the results. How? Apparently, they were asked if a phrase had commercial intent of not and their answers were correlated with the algo’s results.

We aren’t given any idea of how these human evaluators were chosen or why. Was there something that made these particular humans any more well-equipped to make that determination than others? Do they have an specific expertise in evaluating commercial intent? Did the testing involve 2 testers or 20,000? MSN’s explanation of the study doesn’t say.

So, I dug a little deeper and read the original research paper on Commercial Intent Detection presented by MSN engineers in 2006. I found that the study was based on the opinions of just 3 human evaluators:

We asked 3 human labelers ro label the search queries and pages. Each query or page is labeled as “commercial”. “non-commercial”, or “confused”. Each query was labeled by the 3 labelers separately. After labeling process on queries, we keep the queries/pages that were agreed by at least two labelers with non-confused labels.

What????? Are they kidding? I’m no scientist, but this seems like a very flawed process. Was any of the data cross-checked with the conversion tracking systems of real websites to confirm whether searches for those terms actually resulted in a sale or not?

My Simple Test 

Here are the results of a quick test I did using the tool. 1.0 is a 100% probability, so I interpret a .8478 as about 85%. The first column is the search term and the second column is the percentage of probability of commercial intent of the searcher:

snap1.jpg

I think that pretty much demonstrates the tool’s usefulness - or lack thereof - in evaluating keyword phrases.

How It Could Be Improved 

Chances are, we all have at least 3 people on staff who are very well-qualified to label a keyword phrase as having commercial intent or not. Why? Because they regularly view and analyze online sales through sophisticated tracking software. They know the phrases that brought buyers into the websites they manage and the click paths they took once there. Maybe next time, MSN adCenter Labs could at least use experienced Search Engine Marketers as their human labelers and, by using enough of them (way more than 3!), they may get useful data.

Commercial Intent of Web Pages 

The second function of the tool is interpreting the commercial intent of a web page. However, there’s no information at all that tells you how MSN adCenter Labs accomplishes that. I tried entering pages with and without ads on them and pages with BUY NOW! all over them and couldn’t really come to any conclusions. This part of the tool doesn’t even have any entertainment value.  

Conclusion

The most discouraging thing about MSN’s Commercial Intent Detection Tool is that nothing about it appears to have improved since it was released. It is what it is and it’s not likely to get any better.

I’m afraid I can’t put much stock in this tool as something useful for serious marketers. I think your own experience and instincts can give you much better insight to the commercial intent of a search phrase. Of course, we all have tracker data to fall back on when we really want to interpret commercial intent in a meaningful way.

Images Displaying in Google Maps Results

Friday, May 9th, 2008

One of my favorite things about Google Maps is how it constantly evolves. New features are being added all the time and often occur without any noise or fanfare. This morning, for the first time, I saw images being displayed in the Maps results. I searched for “winter park co” and here’s what displayed:

snap6041.jpg

Here’s what a regular Google Search for the same query returned:

snap6042.jpg

I must have been snoozing! Take a look at what you see when you click on the new feature “Explore This Area”:

snap6043.jpg

And this is what you’ll see on the Map next to it:

snap6045.jpg

Why is this significant? Is it the beginning of all relevant results displaying within Google’s verticals?  Images and videos are already in the Maps results. Will local news start appearing, as well?

I certainly don’t know, but it’s great to see another cool feature in Maps. Stayed tuned as the search story unfolds…

Blizzard Named to Top SEO List for May 2008

Monday, May 5th, 2008

spring snowMay 1st was all about blizzards – Colorado was pummeled with a random May Day snowstorm, and Blizzard Internet Marketing was included on the prestigious list of the world’s top Organic Optimization firms!

Each month, TopSEOs.com evaluates Internet Marketing companies in a variety of categories, and based on a set of factors has ranked Blizzard Internet Marketing #21 in Organic Optimization for May.

TopSEOs criteria to rank the top Internet Marketing firms include: client feedback, customer service, competitive advantage, and overall performance.

Top SEOS 2008

What sets our Glenwood Springs based company apart from other Search Engine Optimization firms? Blizzard Internet’s experts are among the top authorities in SEO: Carrie Hill and Mary Bowling are speakers at invitation only conferences, regular contributors to respected industry publications, and attend numerous SEO symposiums to stay on top of up tomorrows’ trends.

Having top Internet Marketing authorities on the team means that Blizzard Internet clients are the first to benefit from the latest best practices SEO and see results in top search engine rankings.

We’d like to thank our clients for their constant support and trust, we’ll be sure to keep you updated on future Blizzard successes!

Should You Put Keywords in Your URLs?

Wednesday, April 23rd, 2008

The answer is a resounding YES! If you want to know why, read on…

Your URL displays in the SERPs

If your URL shows a crazy long string of symbols and numbers, it doesn’t tell the reader much at all:

snap6027.jpg

However, look at the URLs in these listings:

snap6025.jpg

snap6028.jpg

Just by looking at the URL, you can tell where they are and what they do. Sure, the context around them can do that as well. However, the URL gives us one more clue that the listing is about what we are looking for.

It Adds Relevance for the Search Engines

Just as keywords in the URL make a page more relevant for a human reader, it bolsters relevance for the Search Engines, too. If you’ve named a page www.emeraldislegolf.net/DiscGolf.html, like this one:

snap6029.jpg
it is likely to be about disc golf on Emerald Isle.

It Makes It Easy to Organize Your Website

If your pages are named for what they are about (like disc golf above) it becomes very easy to organize your website in a logical way and to talk about your pages in a manner that’s clear to all. You have a disc golf page, a photo page, a youth golf page, etc and everyone can tell which is which. When these are coupled with emeraldislegolf in the domain name, it becomes even clearer what the website and its pages are about.

It was once considered a spammer’s trick to put keywords in a URL, but that has changed. Now, Google officially recommends it in their Webmaster Central Blog.

 

Video Optimization Tips - SES NYC 2008

Wednesday, March 26th, 2008

I attended numerous sessions on video optimization at the recent Search Engine Strategies Conference and Expo held in New York City. Here’s a comglomeration of the best suggestions from a variety of experts on the subject. Most of these are recurring themes that several speakers agreed upon.snap4000.jpg

Use the Google Video Site map feature within Google’s Webmaster Console to submit your videos to the Big G, rather than uploading them to Google Video. Why? Because Google’s pages will outrank yours of there is duplicate content in both places.

Host your own videos on your website for the best SEO benefit. This uses bandwidth, but gives you complete control of your videos. If you have a video that goes viral and it’s not hosted on your site, you’ll be kicking yourself for it.

Relevancy in video is different. In regular search, relevancy is text based. In video, the community helps to determine relevancy - are they watching it and sharing it. How are they tagging it? The rankings often integrate ratings, click through rates, popularity, etc.

Build a separate page on your site for each video and optimize the page for it. Use appropriate title tags, keywords in your content and anchor text links to point to the pages where your videos live. Links to videos matter in the same way that links to pages matter.

Keep all your video files in one directory of your website. This makes it easier for the Search Engines to identify them. Give them good file names, as well.

Optimize your video files to the fullest possible extent. Text still rules in the Search Engines, so wherever you have the opportunity, use text to optimize your videos. This includes the metadata you associate with your videos, as well as the titles, descriptions, categories and tagging you can do when you upload them to sites like YouTube.

Create a video site map page on your website. Optimize it for video site map+keyword phrase. Create and display thumbnails on the page, along with keyword rich text.

To get a video spidered and ranking quickly, link to it from within the content of your home page. You can use the Google Optimizer to refine the best placement for it on the page.

Videos + Creative ideas = Viral Love and lots and lots of links.

Thanks to Steve Espinoza, Li Evans, Gregory Markel, Eric Papczun, Arnaud Mauvais and Jennifer Laylock for all these great insights.

Blizzard’s Mary Bowling Interviewed on WebmasterRadio.fm

Monday, March 24th, 2008

Recently Mary Bowling and myself were in attendance at the Search Engine Strategies New York conference and had the opportunity to sit down and discuss our expertise with WebmasterRadio.fm’s Jim Hedger.

It was a great opportunity and we’re going to be reporting quite a bit of what we learned right here - so stay tuned. But right now here’s Mary’s interview in it’s entirety - Way to go Mary, Great job!

Learn about Local Search

Mary Bowling of Blizzard Internet Marketing on her training session at SES New York on local search


Show Host:
Jim Hedger

Show: Search Engine Strategies


Channel: Conferences



SES NYC Small Business Blitz

Thursday, March 20th, 2008

Yesterday, Blizzard’s own Carrie Hill moderated a great session at the Search Engine Strategies Conference & Expo in New York City. Small Business Blitz addressed the needs of enterpreneurs trying to promote their enterprises online while working within their small budgets.

The first panelist was Stoney de Geyter of Pole Position Marketing. Among his tips were these suggestions about determining your searchers’ intent and applying that knowledge to your optimization.

Keyword Organization

After completing your keyword research, Stoney recommends dividing your terms into categories by searcher intent. The three categories are:

  • Researchers - those just beginning to research something on online or those who are only trying to learn about something and may never have intentions of buying anything.
  • Shoppers - those in a phase of narrowing their focus. They think they want to buy something, but need to do more research before they are ready to plunk down their money.
  • Buyers - those who know what they want and are ready to buy. At this phase, they are comparing features and prices and trying to decide who to by from.

de Geyter then suggests making certain that during optimization you match up each term and its type with a page that satisfies the needs of the type of search they have embarked upon.

Stayed tuned later for more tips from Jennifer Laylock and Matt McGee.