Researcher Jim Jansen On The Sex Of Search Queries
Personalization
**
**
by Gord Hotchkiss
**
In this column, I�ll follow up on my conversation with Dr. Jim Jansen
from Penn State and his recent investigation into behavior patterns
that lie within a large data set of visitor and search advertising
campaign data from a high traffic ecommerce site. In part one
<http://searchengineland.com/researcher-jim-jansen-on-the-truths-myths-of-the-search-buying-funnel-27082>
, Jim and I explored whether a search funnel actually exists.
Surprisingly, Jim found that more generic queries, considered by
marketers to be �top of funnel� queries, may be the only search
activity required. He found these terms tended to generate equivalent
or higher ROI than longer, more transactional queries.
Today, I�d like to cover a couple of additional topics that came up
in our conversation: personalization in terms of the �maleness� or
�femaleness� of the query used, and how personalization may play out
on both the desktop and on mobile devices.
Let�s start with the �sex� of queries. Jansen did an interesting
segmentation of the queries in the dataset, using Microsoft�s
demographic tool:
Jansen: We took queries from this particular search engine marketing
campaign and classified them based on gender probability using
Microsoft�s demographic tool, which will classify a query by it�s
probability of being male or female. We looked at it this way: not
whether the searcher was male or female but did the particular query
fit a gender stereotype—did it have a kind of a male, for example,
feel to it or stereotype implications?
Having done previous work with personalization, and gender
specificity does fall into a broad category of personalization, Jansen
had his own hunches about what he found. As it turned out, his hunches
were wrong:
Jansen: The results to me were counterintuitive from what I expected.
Usually, the idea of personalization is that the more personalized you
get, the higher the payoff, the efficiency and effectiveness is. [But
when we looked at the data] in terms of sales, far and away the most
profitable were the set of queries that were totally gender-neutral.
We took the queries and divided them into seven categories: �very
strongly male,� �generally male,� �slightly male,� �gender neutral,�
�slightly female,� �strongly female,� �very female.� By two orders of
magnitude, the most profitable were the ones that were totally
gender-neutral.
Jansen offered examples of �gender neutral� terms:
Jansen: We defined gender-neutral to be were queries that the
Microsoft tool classified up to like 59% either side. So we had a
fairly big spread here. Here are some examples of queries based off
the Microsoft tool: �electronic chess.� The Microsoft tool classified
that 100% male. For a gender-neutral query—�atomic desk clock� and
�water purifier.�
At this point, the mystery of why �gender neutral� performed at at a
significantly higher level remains to be solved, but Jansen has some
thoughts:
Jansen: One thing that is coming out in the personalization research
is that at a certain level, we have totally unique differences. You
can personalize to a general category and to a certain level, but
beyond that, it�s either not doing much good or may actually get in
the way. And that may be something that is happening here—that these
particular, very targeted gender keyword phrases are just not
attracting the audience that the more gender-neutral queries and
keywords are.
Again, it�s a �why� thing. We spend a lot of time in web search
trying to personalize to the individual level and really haven�t got
very far. But now people are trying to do things like personalize to
the task rather than the individual person, and there�s some
interesting things happening there. Spell checks and query
reformulations and things like that are very task-oriented rather than
individual searcher oriented.
Dr. Jansen�s point about how personalization might be better aimed at
the tasks we�re engaged in rather than the people we are led to
further speculation about where personalization might take us in the
future.
Jansen: is just so hard to do. You know, Gord is
different than Jim, and Gord today is different than Gord was five
years ago. Personalizing at the individual level is just very
difficult and may not even be a fruitful area to pursue.
We�re nonlinear creatures, we�re changing all the time. I can�t even
keep up with all my changes and I can�t imagine some technology trying
to do it. It just seems an unbelievably challenging, hard task to do.
I brought up the point that even we don�t know why we do the things
we do, because so much of our decision making is driven by unconscious
factors. It�s a thought that�s crossed Jansen�s mind as well:
Jansen: I�ve commented on that before in terms of recommending a
movie or book to me. I don�t even know what books and movies I like
until I see them. Sometimes I pick up a book and say, �Oh, I�m going
to really love this,� only to get a chapter into it and realize �Okay,
this is horrible.� And I think you see that in the NetFlix
challenge— So many organizations have labored for a decade now, and
finally it looks like perhaps this year someone may win by combing 30
different approaches simultaneously to the very simple problem of
�Recommend a movie. It�s just amazing the computational variations
that are going on.
From personalization, our conversation then veered to mobile (not
such a long detour, really). To me, the intersection of search and
functionality has the most potential on our mobile devices. But the
need to �get it right� is substantially higher, given the inherent
challenges of handheld devices: limited screen real estate and input
challenges.
Jansen: Everybody is saying (again), �This is the year mobile
searching�s going take off.� It�s been going on for four or five years
now, and really, at least here in the US, it hasn�t really happened
yet. But what I think is going to make it hit the mainstream is this
combination of localized search. When you have a mobile device, the
technology has so much more information about you: it�s got your
location to within a couple feet, the context that you�re in can
really start entering the picture and information gets pushed to
you—I�m thinking tagged buildings and restaurants and cultural
events and on and on. And so with my mobile device, where I can talk
into it, I don�t even have to type anything. I want �what�s going on
in the area?� and it automatically knows my location and the time and
perhaps something about me and the things that I�ve searched on
before. �Oh, you like coffee shops where there�s some music playing.
Guess what? Boom. There�s five right near, in your area that have live
entertainment right then.� So I think in that respect it�ll be a
little more narrowed search, but the technology will have so much more
information about us that in a way it makes the job easier. The
problem�s going to be the interface and the presentation of the
results.
Imagine being able to walk through a town& I live in Charlottesville,
Virginia. Tons of history here from 400 years ago when Europeans first
settled here, Thomas Jefferson, James Madison, etc., etc. Being able
just to walk down Main Street and have tagged buildings interface with
my mobile device� I�m a big history buff and so getting that
particular information, one, pushed to me or at least available to
push when I ask for it is a wonderful, wonderful area of
personalization. This idea of localized search and mobile devices and
mobile search may be the thing that brings it all together and makes
mobile search happen.
Given the direction of conversation I had to ask Jim about the
privacy implications of all this functionality. Let�s assume that
Google is the likely candidate that assemble this search �utopia.�
What price might we have to pay to enable Google�s effectiveness as
our own personal digital concierge, or, more sinisterly, our �Big
Brother?�
Jansen: You know, the �Big Brother� idea label has certain negative
connotations, so I don�t want to say that Google is Big Brother-ish in
that regard. But certainly I think with their movement into free voice
and free directory assistance, they will soon have a voice data
archive that will allow them to do some amazing things with voice
search, which would be an awesome feature for mobile devices. Being
able to talk into a mobile device, have it recognize you nearly 100%
of the time and execute the search.
My final question for Jim was how much of a priority should Google
make innovation in the mobile search space:
Jansen: Google of course is the one that knows what they�re doing,
but certainly I think it would be naive not to be exploring that
particular area. And I think the contrast from what you said about
Microsoft and the desktop, the desktop is just so busy. You�re getting
so many different signals in terms of business, personal things, my
kids use my computer sometimes. And so the context is so large on the
desktop, but the mobile device, it�s narrower. You know, you have some
telephone calls, you can do some GPS things, so the context is
narrower but very, very rich in that very narrow domain. I think it�s
a really hot area of search.
The entire interview transcript has been posted
<http://www.outofmygord.com/archive/2009/10/26/Talking-Search-with-Jim-Jansen-at-Penn-State.aspx>
to my blog. As always, a conversation with Jim Jansen never fails to
be interesting.
Opinions expressed in the article are those of the author, and not
necessarily Search Engine Land.
Gord Hotchkiss <http://searchengineland.com/author/gord-hotchkiss/>
is CEO of Enquiro <http://www.enquiro.com/>
, a search marketing firm that produces search engine user eye
tracking studies <http://www.enquiro.com/eyetrackingreport.asp>
and other research.
<font size="-1">
Upcoming Search Marketing Expo events you won't want to miss:<ul><li><a
href="http://searchmarketingexpo.com/west/?utm_source=newsletter&utm_medium=text&utm_content=footertext&utm_campaign=SMX%2BWest%2B2010">SMX
West - Santa Clara, CA</a> - March 2-4, 2010</li><li><a
href="http://searchmarketingexpo.com/advanced/?utm_source=newsletter&utm_medium=text&utm_content=footertext&utm_campaign=SMX%2BAdvanced%2B2010">SMX
Advanced - Seattle, WA</a> - June 8-9, 2010</li><li><a
href="http://searchmarketingexpo.com/munich?utm_source=newsletter&utm_medium=text&utm_content=footertext&utm_campaign=SMX%2BMunich%2B2010">SMX
Munich</a> - March 23-25, 2010</li><li><a
href="http://www.searchmarketingexpo.com.au/?utm_source=newsletter&utm_medium=text&utm_content=footertext&utm_campaign=SMX%2BSydney%2B2010">SMX
Sydney</a> - April 22-23, 2010</li></ul>Attend a <a
href="http://searchmarketingnow.com/?utm_source=newsletter&utm_medium=email&utm_content=textlink&utm_campaign=SMN%2Bgeneral">Search
Marketing Now</a> Webcast - it's free! Upcoming webcasts:<ul><li><a
href="http://searchmarketingnow.com/webcasts/wc091028">Managing Search
Marketing Success at the C-level: What Your CMO Should Know</a> - October
28, 2009</li><li><a
href="http://searchmarketingnow.com/webcasts/wc091103">Ask iProspect: PPC
Strategy & Tactics from the Experts</a> - November 3, 2009</li><li><a
href="http://searchmarketingnow.com/webcasts/wc091112">PPC Advertising &
Geo-Targeting</a> - November 12, 2009</li></ul>Interested in advertising or
sponsoring Search Marketing Expo or Search Marketing Now webcasts? <a
href="http://thirddoormedia.com/contact/sales.shtml?utm_source=searchcap&utm_medium=email&utm_content=textlink&utm_campaign=General%2BSales">Contact
us</a>.
<div><a href="http://www.superbhosting.net/"><img
src="http://www.searchmarketingnow.com/_images/superb.gif"
border="0"></a></div>
You are receiving this email because you subscribed to a Search Engine
Land, Search Marketing Now or Search Marketing Expo newsletter. To update
your subscriptions or unsubscribe, use your newsletter preferences page at
http://third.thirddoormedia.com/lists/?p=preferences&id=2&uid=f9779113b77d03598707df46ae032f9b.
Or send your written request to: 279 Newtown Tpke., Redding, CT
06896</font>
--
Powered by PHPlist, www.phplist.com --
0 comments:
Post a Comment