March 24, 2008 1 Comment
Two recent posts on the implicit web provide two different takes. They provide good context for the implicit web.Richard MacManus of ReadWriteWeb asks, Aggregate Knowledge’s Content Discovery – How Good is it, Really? Aggregate Knowledge runs a large-scale wisdom of crowds application, suggesting content for readers of a given article based on what others also viewed. For instance, on the Business Week site, you might be reading an article about the Apple iPod. Next to the article are the articles that readers of the Apple iPod article also viewed. MacManus finds the Aggregate Knowledge recommendations to be not very relevant. The recommended articles had no relationship to Apple or the iPod.
Over at CenterNetworks, Allen Stern writes that Toluu Helps You Like What Your Friends Like. Toluu lets you import your RSS feeds and friends who have also uploaded their RSS feeds. It applies some secret sauce to analyze your friends’ feeds and create recommendations for you. Stern finds the service a bit boring, as all the recommendations based on his friends’ feeds were the same.
In the case of Aggregate Knowledge, the recommendations were based on too wide a pipe. The implicit actions – clicks by everybody – led to irrelevant results because you essentially the most popular items. In the case Toluu, the recommendations were based on too narrow a pipe. The common perspectives of like-minded friends meant the recommendations were too homogeneous.
Both of these companies leverage the activities of others to deliver recommendations. The actions of others are the implicit activities used to improve search and discovery. A great, familiar example of applying implicit activities is Google search. Google analyzes links among websites and clicks in response to search results. Those links and clicks are the implicit actions that fuel its search relevance.
Which leads to an important consideration about implicit activities. You need a lot of explicit activity to have implicit activity.
That’s right. Implicit activities don’t exist in a vacuum. They start life as the explicit actions of somebody. This is a point that Harvard’s Andrew McAfee makes in a recent post.
Let’s take this thought a step further. Not all explicit actions are created equal. There are those that occur “in-the-flow” and those that occur “above-the-flow”, a smart concept described by Michael Idinopulos. In-the-flow are those actions that are part of the normal course of consumer activities, while above-the-flow takes an extra step by the user. A couple examples describe this further:
- In-the-flow: clicks, purchases, bookmarks
- Above-the-flow: tags, links, import of friends
Above-the-flow actions are hard to elicit from consumers. There needs to be something in it for them. Websites that require a majority of above-the-flow actions will find themselves challenged to grow quickly. They better have something really good to offer (such as Amazon.com’s purchase experience). Otherwise, the website should be able to survive on the participation of just a few users to provide value to the majority (e.g. YouTube).
So with all that in mind, let’s look at a few companies with actual or potential uses of the explicit-implicit duality:
In an interview with VentureBeat, Google VP Marissa Mayer talks about two different forms of social search:
- Users label search results and share labels with friends. This labeling becomes the implicit activity that helps improve search results for others. This model is way too above-the-flow. Labeling? Sharing with friends? After experimenting with this, Mayer states that “overall the annotation model needs to evolve.” Not surprising.
- Google looks at your in-the-flow activity of emailing friends (via Gmail). It then marries the search histories of your most frequent email contacts to subtly alter the search result rankings. All of this implicit activity is derived from in-the-flow activities. For searches on specific topics, the more narrow implicit activity pipe of just your Gmail contacts is an interesting idea.
ThisNext is a platform for users to build out their own product recommendations. They find products on the web, grab an image, and rate and write about the product. Power users emerge as style mavens. The site is open to non-members for searching and browsing of products.
ThisNext probably relies a bit too heavily on above-the-flow activities. It takes a lot of work to find products, add them to your list of products and provide reviews. It also suffers from being a bit too wide a pipe in that there’s a lot of people whose recommendations I wouldn’t trust. How do I know who to trust on ThisNext?
Amazon, on the other hand, has a leg up in this sort of model. First, its recommendations are built on a high level of in-the-flow activities – users purchasing things they need. This is the “people who bought this also bought that” recommendation model. Rather than depend on the product whims of individuals, it uses good ol’ sales numbers (plus some secret sauce as well) for recommendations. This is a form of collaborative filtering.
Amazon Grapevine is a way of setting the pipe for implicit activities. The explicit activity is the review or rating. These activities are fed to your friends on Facebook. One possibility for Amazon down the road is to use the built-up reviews and ratings of your friends to influence the recommendations it provides on its website. Such a model would require some above-the-flow actions – add the Grapevine application, maintain your account and connections on Facebook. But these aren’t that onerous; the Facebook social network continues to be an explicit activity that has high value for individuals.
Yahoo bought the bookmarking and tag service del.icio.us back in 2005. It’s hard to know what, if anything, they’ve done with that service. But one intriguing possibility was hinted at in this TechCrunch post. The del.icio.us activity associated with a given web page is integrated into the search results. Yahoo search results would be ranked not just on links and previous clicks, but also on the number of times the web page had been bookmarked on del.icio.us. And, the tags associated to the website would be displayed, giving additional context to the site and enabling a user to click on the tags to see what other sites share similar characteristics.
This takes an above-the-flow activity performed by a relative few – bookmarking and tagging on del.icio.us – and turns it into implicit activity that helps a larger number of users. But with the Microsoft bid, who knows whether something like this could happen.
The use of implicit activity is a powerful basis to help users find content. Just don’t burden your users with too much of the wrong kind of explicit activity to get there. Two factors to consider in the use of implicit activity:
- How wide is the pipe of implicit activities?
- How much above-the-flow vs. in-the-flow activity is required?