4 replies to this topic

[iamlost]

Very interesting interview:
Gord Hotchkiss interviews Jakob Nielsen on the future of the SERP (and other stuff)

I think there is a tendency now for a lot of not very useful results to be dredged up that happen to be very popular, like Wikipedia and various blogs. They’re not going to be very useful or substantial to people who are trying to solve problems. So I think that with counting links and all of that, there may be a change and we may go into a more behavioral judgment as to which sites actually solve people’s problems, and they will tend to be more highly ranked.
...
...that search results have been 1 dimensional, which is linear, just scroll down the page, and so potentially 2 dimensional (they can call it three but it is two) that is the big step, doing something differently and that may take off and more search engines may do that if it turns out to work well. But I think it’s more likely that they will work on ways on integrating all these different sources into a linear list.
...
All this stuff..all this talk about personalization, that is incredibly hard to do. Partly because it’s not just personalization, based on a user model, which is hard enough already. You have to guess that this person prefers this style of content and so on. But furthermore, you have to guess as to what this person’s 'in this minute' interest is and that is almost impossible to do. I’m not too optimistic on the ability to do that.
...
...that’s actually my third possible change. My first one was changing to the ranking scheme; the second one was the potentially changing to two dimensional layouts. The third one is to add more tools to the search interface to provide query reformulation and query refinement options. I’m also very skeptical about this, because this has been tried a lot of times and it has always failed.

A very meaty interview. Still digesting. Wrote a page of points to consider, research, and develop.

[rhianna]

I found Jacob Nielsen's analogy of pictures used in sites (and subsequently found in [image searching] search engines) with "banner blindness" to be really interesting.
(1)Will people tire of the image search engines?
(2) How can webmasters create their pages so that if a web page is found via an image search engine, that the "hit" will be less likely wasted bandwidth and more likely to be productive for both the user and the webmaster's intent?

I would really say tweak it such so that you only put it up when you’re really sure that it’s a highly relevant good image. If there starts becoming that there are too many images, then we start seeing the obstacle course behavior... And then people involve behavior where they look around the images which is very contrary to first principals of perceptual psychology type of predicting which would be that the images would be attractive. Images turn out to be repelling if people start feeling like they are irrelevant. It’s a similar effect to banner blindness. [source]

As a webmaster I've noticed that sections of my site gets searched mainly through Google's image search.
Some of my own images attract a number of "hits" and others are attracted to certain "affiliate products."
I often go to the person's search results to try to figure (1) what was the person looking for [really] and (2) are there any new key words that I could include in my existing page or could I build a new page around a related concept?
Nielsen highlights an important point when he suggest that people using the Internet will grow tired of "stock photos of glamour models" that may look beautiful but don't address the questions the user is trying to answer.

Google's image searching capability was introduced with some fanfare much like Deja News when it gave people the ability to search through usenet newsgroups. Although Google appropriated Deja News into its own Google News, usenet itself is not as popular as it once was. People still probably search through usenet groups, but that function is not as important as it once was. How much longer will people be excited about image searching if the results are canned images found all over the Internet?

Nielsen addresses an excellent point about tweaking images on one's page to make sure that they are "highly relevant." Which are more relevant? Glamorous pictures of models or pictures of the home brewed categories?

[bragadocchio]

I'm seeing things from a very different perspective than Dr. Nielsen here.

I don’t think there will be that big a change because 3 years is not that long a time. I think if you look back three years at 2004, there was not really that much difference from what there is today.

Seems that there have been a few changes since 2004. Here are some from Google:

1. Integration of vertical search results into the search results set page, including maps, working videos, images, hotel/flight/transit dropdowns, product/book/music results, news results, definitions, Q&A results, and others.

2. Query revisions in the middle of search results pages, based upon user behavior information

3. Query revisions at the tops or bottoms of pages based upon Google Base/Custom Search Engine results/labels.

4. Reranking of results based upon country preferences, language preferences, personalization, others.

5. Sitelinks that attempt to anticipate final destinations in the top result.

One of them that will not make any difference to the appearance and that is a different prioritization scheme. Of course, the big thing that has happened in the last 10 years was a change from an information retrieval oriented relevance ranking to being more of a popularity relevance ranking.

Funny thing here is that the "popularity" relevance change was the innovation that PageRank brought in 1998 - about ten years ago. The move now seems to be on integrating more user behavior and more advanced information extraction into results. The move realistically, is from a popularity relevance ranking to a recommendation system that attempts to understand individual information needs better.

I think there is a tendency now for a lot of not very useful results to be dredged up that happen to be very popular, like Wikipedia and various blogs.

Wikipedia does a lot of stuff right from an SEO perspective, and it's more likely that the high rankings of wikipedia pages is due to site structure, page and code layout, use of categories and internal linking and page improvement policies that increase links between pages and the quality of content of those pages. The high number of links to pages of wikipedia don't hurt, also. Many wikipedia pages are useful as starting points in conducting research.

On the other end of the spectrum, many blogs are written by people who are experts in a particular field, and who provide very useful results. Jarod Spool's blog Brain Sparks, for example.

It’s just going to be that the top one is going to be the one that the various search engines, by what ever means they think of, will judge to be the best and that’s what people will tend to click first, and then the second one and so on.

I agree that user behavior is a driver in changes, and in reranking pages. But, the movement is towards reranking based upon the intents of individual searchers. I'm not sure that he gets this. A search for [java] might mean coffee for me, a programming language for someone else, and an island for another person. The search engines don't want to find the "best" page, but rather the "best" page for the person conducting the search. That's a difference that is significant.

More in another post or two.

[bragadocchio]

Nielsen highlights an important point when he suggest that people using the Internet will grow tired of "stock photos of glamour models" that may look beautiful but don't address the questions the user is trying to answer.

Perhaps a reason that you would want to insert images from places like Flickr into your search results instead of from stock galleries of images taken from professional photographers. See:

Flickr Photos Integrated into Yahoo Image Search

What they have done very well is this “just in time” relevance or “cross sell” as it’s normally called. So when you are on one book on one page, or one product in general, they will say, here are 5 other ones that are very similar to the one you’re looking at now. But that’s not saying, in general, I’m predicting that these 5 books will be of interest to you. They’re saying, “Given that you’re looking at this book, here are 5 other books that are similar, and therefore, the lead that you’re interested in these 5 books comes from your looking at that first book, not from them predicting or having a more elaborate theory about what I like.

That's not how Amazon's item-to-item collaborative filtering works. I'd recommend that Dr. Nielson start reading Greg Linden's blog (the inventor of Amazon's item-to-item collaborative filtering). It's a blog, and we know that Dr. Nielsen doesn't find that those possess any value. But, he's wrong. Fortunately, there are some articles on the subject, too. Here's one from 2003:

Amazon.com recommendations: item-to-item collaborative filtering

That's subscription only, but it's based upon the patent filed in 1998, which is available from the USPTO:

Collaborative recommendations using item-to-item similarity mappings

[cvos]

Personalization is already here to a limited extent. When logged into your google account, SERP's can vary slightly. I do a lot of searches related to one of my clients who has a 4 letter .net name. If i am on my computer a search for XXXX brings up my client, while on public computers it brings up XXXX.com