A woman says to a man, “It’s cold in here.” The man puts his arms around her and holds her. He could have turned up a thermostat, or brought her a sweater, or asked her if she wanted to go somewhere warmer. But imagine that the man and woman are in a relationship and have had that conversation many times in the past, and both easily understood the intention behind the words.
We can sometimes understand the intent behind certain words even though the words don’t match up well with the people who voice them, though the intentions behind words can be difficult things to understand. Sometimes nonverbal communication that accompanies words can help interpret them, though humans aren’t necessarily that good at reading nonverbal communication.
Sometimes experience can be informative in understanding what certain words might mean, like the man and woman in my example above.
If human beings can grow easily confused about the intentions behind words, how well can a computer understand the intent behind a handful or fewer words in a query at a search engine?
That’s a challenge that search engines face as they try to strive to serve one set of search results to one visitor and a different set of results to another based upon things like location or preferred choice of language or past searching and browsing history.
Erik Selberg provides his thoughts on an upcoming Microsoft search upgrade in his post “first impressions.” The codename for the upgrade appears to be “Kumo,” which may also end up being the new name of Microsoft’s search. The name “Kumo” can mean “spider” or “cloud” in Japanese.
Dr. Selberg is one of the founding members of Microsoft Search Labs and worked on helping to create and define the algorithms behind the relevance of MSN Search and Live Search. His thoughts about a possible screenshot of upgraded search results from Microsoft are interesting, especially this one:
Then there are related searches, and then a fascinating section: â€œyour history.â€ So, it looks like theyâ€™re finally going to start to show you your previous searches and possibly let you do something with them! Itâ€™s about time some of that work started to see the light of day! 🙂
Interestingly, a patent application filed this week from Microsoft lists Erik Selberg as the inventor and gives us a glimpse at one kind of personalization from Microsoft that might someday be seen in the light of day. Whether or not it’s the personalization that we see with Kumo is unknown. We might also see something like Microsoft’s U Rank, which shares many similarities with Google’s Search Wiki.
Best Answers For Different Searchers
The patent filing is worth looking at more deeply, regardless of whether it’s part of what Microsoft rolls out when they release their search upgrade.
The basic premise is that when two different people are searching for the same query term, the chances are that the answers that they are trying to find or the sites that they might want to see are different and that a search engine might be able to help each of those searchers find what they are looking for based upon experience, and past searches and search result selections.
If someone has performed the same or a substantially similar search a few times in the past and tends to choose a particular result in response to those searches, then that site might be seen as the desired result for that searcher in the future. A similar search might be, for instance, one in which 8 of the top 10 search results are the same for each query term.
What if, in future searches for that searcher, the site that they tend to pick is displayed in a different manner, such as bolded, or highlighted, or shown with a border, or in a different font than the other search results? What if it is placed at the top of the results instead of where it might normally be? The idea behind the different presentations being to make it easier for the searcher to pick out that site as one that might be preferred.
The patent application is:
Presenting Result Items Based Upon User Behavior
Invented by Erik Warren Selberg
Assigned to Microsoft
US Patent Application 20090063460
Published March 5, 2009
Filed August 31, 2007
The concept of “Personal Definitives” is at the heart of the patent filing.
A personal definitive is the “best” answer to a given search query as it relates to a specific searcher. Information collected to identify a searcher’s personal definitives include such things as:
- Cookie or login information,
- Terms or phrases used to search upon in the past,
- Search results or a representation of those results in response to queries, and;
- Selection counts for previously presented search results.
If you tend to search using the same or a substantially similar query term or phrase and tend to select the same page or pages in response to that search, don’t be surprised if, at some point, it might be highlighted or bolded or placed at the top of the search results in the future.
While this is something we might see at Microsoft, it wouldn’t be surprising to see something similar spring up at Google or Yahoo in the future as well.
Whether past searches are a good indication of intent for searches in the future?
Sometimes the statement “It’s cold in here” isn’t an invitation to a hug but rather a request to turn up the thermostat.
20 thoughts on “Understanding Intentions and Microsoft Search Personalization”
I think basing search results and rankings based on people’s past search behavior could really get in the way of offering the person newer, more current and relevant results.
What was that old quote, something about the definition of “insanity” is doing the same thing over and over and expecting to get a different result. That seems to apply to the idea behind this search algorithm as well.
Interesting patent application but to be honest I’m also not convinced that past search history should play a part in current search behavior. It could also work both ways and, if anything, searching again for similar information could indicate that previous search results weren’t satisfactory.
Past search history can be one of the several factors basis which results are generated. However, search-by-intent (semantic, to be more specific) as against search-by-content, can really go wrong if not implemented smartly. Personalization also means, the ‘person’ can decide when to turn off ‘personalization’.
Hi People Finder,
I agree with you that basing future actions on past behaviors can have a negative side. It can hinder the discovery of new and better resources. I hope that if something like this is implemented, that care is taken to not overwhelm searchers with selections of previous pages that they viewed, so that it doesn’t limit other alternatives. I guess the same complaint can be made about the search selections that show up in dropdowns when you type a query into a search engine – instead of people finishing their queries, they might choose instead to look at the same things that everyone else is viewing. That can limit research and creativity, and keep more unique queries from being made.
Hi Business Marketing,
I think there is a helpful side to marking results that they might have viewed before in a unique manner, as described in the patent filing. I might just use it in an unintended way though, but ignoring many of the sites that I’ve already seen, and looking at new ones.. 🙂
You’ve mentioned one of my pet peeves when it comes to search – the inability to turn off some personalization features.
When I’m searching at Google, and I see a message at the top right of the search results that they have been customized based upon my previous searches, I get really concerned that I’m possibly missing something that I would like to see. One thing that bothers me about that is that I have no idea of how they are transforming my search results through their customization, and have no way to turn that customization off.
While a search engine can guess at intent, ultimately I’m the only one who really knows for certain what my intent was.
Every once in a while I hear about those “new reolutionary search engines” that are going to “change the way we’re searching forever”. However they never do. And I don’t have high hopes for Kumo neither.
I imagine that it has to feel risky for a search engine that does receive lots of traffic and searches to transform the way search results look and feel overnight. I think many of the changes that we see in search at the major search engines have been behind the scenes, where they might be less visible.
But, consider the inclusion of images, videos, news, blog results, book results, and other things that were brought to us by Universal and blended searches, and we have seen some really interesting changes. Personalized search is bringing us further and further from seeing the same search results as everyone else when we type in the same words for a search query.
I don’t understand it. I search for Summertime fantasies and I keep getting Bill Slawski and this SEO By The Sea site. What’s up with that? 😉
I don’t need a search engine to find what I need in life and love – I’ve found the answers to those questions with you. Thank you, my love. ♥
Ah, but without an SE, I wouldn’t have found YOU. Then how could I have optimized my charm and flirt ability?
Ok, Summertime fantasies: Check
What shall I search for now Mr Slawski? Lemme see…
Search: A million and one ways to smooch?
Good thing for search engines then, Kimberly. May we get the chance to search together for an eternity.
Well it’s been awhile and Microsoft Personalized Search has not change the way we search and I still don’t get it really.
I’m not sure how much Bing is personalizing search results these days.
Comments are closed.