Just Behave: Google’s Marissa Mayer on Personalized Search

It was almost 3 weeks ago today that Google posted on their corporate blog about some changes to the personalized search sign-up process. Danny covered this development quite nicely in a very comprehensive post, looking at the specifics of the announcement and what it means for users.

The announcement and the subsequent posts have set off a minor firestorm of blogging activity as many of us, myself included, have joined in the debate of what personalized search means, both for users and for the SEO industry. My position has consistently been that personalization of search results is inevitable. It’s the foundation for improving the search experience in the future.

This is not really a new message, as the engines, particularly Google, have been touting the benefits of personalization for some time. In fact, it was a strategic initiative that was mentioned by Eric Schmidt in a speech dating back to 2003. For many of us, the recent Google announcement served as a warning that personalization’s day is rapidly approaching and the day of the universal search results page will soon be over for many queries.

The day after the announcement came out, I sent an e-mail to Marissa Mayer asking for an interview to talk about what personalization means for the user experience on Google. We managed to connect this week and I had the chance to ask her about some of the feedback, both good and bad, that has been emerging on various blogs. In this column I’ll include some excerpts from the interview, as well as my thoughts about what this might mean for both marketers and users in the future. For a full transcript of the interview, please check out this post on my blog.

The changes didn’t really affect how personalized search worked on Google. That remains pretty consistent with what it was before the announcement. The change is, however, signaling a more aggressive stance by Google in pushing more users towards the personalized search experience. In many circumstances, personalized search now represents the default, “on” option for most users. It ties together three distinct personalization products previously offered by Google, and integrates them more tightly as the default user option. This includes search history, personalized search results and a personalized homepage. Also, in a move to make determining whether you’re logged in or locked out more apparent, Google has “cleaned up” the process and made it more apparent to the user. Mayer said:

We’ve had a very impressive suite of personalized products for awhile now: personalized homepage, search history, the personalized webpage, but we haven’t had them integrated, which I think has made it somewhat confusing for users. A lot of people didn’t know if they had signed up for search history or personalized search; whether or not it was on. What we really wanted to do was move to a signed in version of Google and a signed out version of Google. So if you’re signed in you have access to the personalized home page, the personalized search results and search history. You know all three of those are working for you when you’re signed in. And if you’re signed out, meaning that you don’t see an email in the upper right hand corner that personalized search isn’t turned on. If anything, it’s a cleaning up of the user model, to make it clearer to users what services they’re using them and when they’re using them.

Early in the interview, I asked Marissa what led to this more aggressive “opt in” move by Google. I also mentioned that with the only notification that you’re seeing personalized search results now being (with the disappearance of the “turn off personalized search results” link) your e-mail address appearing in the upper right-hand corner, a section of the page that most people wouldn’t look at once they’re engaged in the act of searching, there should be a corresponding increase in personalized search activity.

Actually I don’t think it will change the volume of personalized search all that much, not based on what we’ve seen on our logs and usage. I do think that over time, what it does is it pushes the envelope of search more such that you expect personalized results by default. And we think that the search engines in the future will become better for a lot of different reasons, but one of the reasons will be that we understand the user better.

The answer seemed a little paradoxical. Personalized search volume probably won’t increase, but increased exposure should build an expectation that users will see personalized search results. In short, it lessens the resistance to personalized search and builds acceptance for future innovations around personalization. Like many aspects of the interview, it’s clear that Google has a definite timeline for personalized search. The rather minor tweaks that we’re seeing now, which may not impact usage numbers greatly in the short term, will gradually give way to a more obvious presence of personalization on the search results page. Another signal of Google’s aggressive stance in encouraging people to adopt personalized search was the less than prominent placement of the opt-out box for new Google account sign-ups. I mentioned this point to Marissa as well, and she said:

I think that falls in with the philosophy that I just outlined. We believe that the search engines of the future will be personalized and that it will offer users better results. And the way for us to get that benefit to our users is to try and have as many users signed up for personalized search as possible. And so certainly we’re offering it to all of our users, and we’re going to be reasonably aggressive about getting them to try it out. Of course, we try to make sure they’re well-educated about how to turn it off if that’s what they prefer to do.

So, if Google is being aggressive in getting people to sign up for personalized search results, how aggressive are they in actually showing the results? In that area in particular they’re treading carefully:

The actual implementation of personalized search is that as many as two pages of content, that are personalized to you, could be lifted onto the first page and I believe they never displace the first result, because that’s a level of relevance that we feel comfortable with. So right now, at least eight of the results on your first page will be generic, vanilla Google results for that query and only up to two of them will be results from the personalized algorithm. I think the other thing to remember is, even when personalization happens and lifts those two results onto the page, for most users it happens one out of every five times.

In those that have criticized personalized search, lack of control seems to be an overriding concern. What if our past search patterns restrict our ability to explore new topics, because Google is giving us the results that it thinks we want to see, based on our search history? Marissa indicated that Google’s intention is to keep the user firmly in control of the search experience at all times:

We’re introducing it in a fairly limited form for exactly the reason that you point out. And I think if we tend to veer towards a model where there are more results that are personalized; we would have ways of making it clearer: “Do you want to explore this topic as a novice or with the personalization in place?” So the user will be able to toggle in a different filter form. I think the other thing to remember is, even when personalization happens and lifts those two results onto the page, for most users it happens one out of every five times. When you think about it, 20% of the queries are much better by doing that, but for 80% of the queries, people are, in fact, exploring topics that are unknown to them and we can tell from their search history that they haven’t searched for anything in this sphere before. There’s no other search like it. They’ve never clicked on any results that are related to this topic, and, as a result, we actually don’t change their query set at all because we know that they need the basic Google results. The search history is valuable not only because it can help personalize the results but they’re also valuable because we can tell when not to.

So this seems to indicate the personalization will have its biggest impact on those search activities that you tend to do on a frequent basis. As you strike out into new territory online, personalization will automatically switch off, preventing it from biasing your search results.

So, how smart is Google’s personalization technology? How good is it now; and how good will it become in the future? How do you maintain a consistent user experience through that evolution? Marissa indicated that this is a move that’s been four years in the making and that they will continue to move at a conservative pace when it comes to introducing personalization into the search experience.

I will say that there are a lot of challenges there and a lot of this is something that’s going to be a pragmatic evolution for us. You have to know that this is not a new development for us. We’ve been working on personalized search now for almost 4 years. It goes back to the Kaltix acquisition. So we’ve been working on it for awhile and our standards are really high. We only want to offer personalized search if it offers a huge amount of end user benefit. So we’re very comfortable and confident in the relevance seen from those technologies in order to offer them at all, let alone have them veered more towards the results, as we’re doing today.

Marissa then proceeded to give me some insight into how personalization currently works on Google. It goes back to an acquisition made in 2003.

We acquired a very talented team in March of 2003 from Kaltix. It was a group of three students from Stanford doing their PhD, headed up by a fellow named Sep Kamvar, who is the fellow who co-signed the post with me to the blog. Sep and his team did a lot of PageRank style work at Stanford. Interestingly enough, one of the papers they produced was on how to compute PageRank faster. They wrote this paper about how to compute page rank faster and it caused a huge media roil around the web because everyone said, there are these students at Stanford who created an even faster version of Google. Because the press obviously doesn’t understand search engines and thinks that we actually do the PageRank calculation on the fly on each query, as opposed to pre-computing it.

Interestingly enough, the reason they were interested in building a faster version of PageRank was because what they wanted to do was be able to build a PageRank for each user. So, based on seed data on which pages were important to you, and what pages you seemed to visit often, re-computing PageRank values based on that. PageRank as an algorithm is very sensitive to the seed pages. And so, they had figured out a way to sort by host and as a result of sorting by host, be able to compute PageRank in a much more computationally efficient way to make it feasible to compute a PageRank per user, or as a vector of values that are different from the base PageRank. The reason we were really interested in them was: one, because they really grasped and cogged all of Google’s technology really easily; and, two, because we really felt they were on the cutting edge of how personalization would be done on the web, and they were capable of looking at things like a searcher’s history and their past clicks, their past searches, the websites that matter to them, and ultimately building a vector of PageRank that can be used to enhance the search results.

Currently, the signals that feed this personalization algorithm come primarily from your past search history and the sites you selected in each of those searches. Of lesser importance are any favorite sites you might bookmark in Google and things you may add to your personalize homepage. But obviously, Google’s ability to learn more about you as an individual increases as they gather more data about you. As Google becomes more integrated into your day-to-day activities on your computer, could this information also be potentially used as a signal to help refine your search?

I think so. I think that overall, we really feel that personalized search is something that holds a lot of promise, and we’re not exactly sure of the signals that will yield the best results. We know that search history, your clicks and your searches together provide a really rich set of signals but it’s possible that some of the other data that Google gathers could also be useful. It’s a matter of understanding how.

There’s an interesting trade off around personalized search for the user which is, as you point out, the more signals that you have and the more data you have about the user, the better it gets. It’s a hard sell sometimes, we’re asking them to sign up for a service where we begin to collect data in the form of search history yet they don’t see the benefits of that, at least in its fullest form, for some time. It’s one of those things that we think about and struggle with. And that’s one reason why we’re trying to enter a model where search history and personalized search are, in fact, more expected. And I should also note that as we look at reading some of the signals across different services we will obviously abide by the posted privacy policies. So there are certain services where we’ve made it very clear we won’t cross correlate data. For example on Gmail, we’ve made it very clear that we won’t cross correlate that data with searches without being very, very explicit with the end user. You don’t have to worry about things like that.

I’m guessing that Google is holding their personalization cards very close to their chest. And you can’t really blame them. The one thing that became clear in the interview is that personalization marks the primary strategic platform for Google’s innovation in the future. When something is as important strategically to an organization as personalization is, one can’t expect any startling revelations about Google’s plans for the future. I tend to agree with Google that personalization marks the most likely path for improvement of our own individual search experiences.

And if this is true, more personalization should be a good thing. Google’s official stance at this point is that they will tread carefully in the introduction of personalization and the fact that they’ve been at this for four years certainly seems to indicate that they’ve shown caution up til now. Marissa also indicated that if personalization becomes a more prominent factor on the search results page, it will come along with making sure that the user has the opportunity to toggle on and off personalized results and potentially a marking that indicates which results are there through personalization.

But, if personalization can dramatically improve the search experience, I have to believe that Google’s implementation of it could be a more aggressive than Marissa indicated in this interview. Certainly, competitive forces with Microsoft and Yahoo will push Google’s introduction of any competitive advantage it might have. The one thing that came through loud and clear, however, is that Google wants more and more of us taking personalized search for a test drive.

Once again, I have posted the full transcript of this interview on my blog.

Gord Hotchkiss is CEO of Enquiro, a search marketing firm that produces search engine user eye tracking studies and other research. The Just Behave column appears Fridays at Search Engine Land.