Key concepts are understanding pages, users, queries. What’s needed (imho) is to understand the context in trends mapped across the global trendbase. Google recently was blasted on images on Google Trends. I personally didn’t see a big problem with it because Google sometime ‘hiccups’ now and then. What most people don’t uderstand is that Google is constantly ‘tweaking’ their algorithms and that it can cause some wierd results. I had a chat about this with Tim O’Reilly on my podcast and he agrees that Google must push the real-time envelope in order to innovate.
This blog post is trying to be a thought-leading (deep dive) blog post on some of their search technology. I think that it falls short in one area. I want the Google fellows to talk about how they are dealing with technology to make “real time’ data more relevant.
Search is changing in the way Google is looking at it but also in other areas. Social search is something everyone is trying to solve. The problem is it’s harder now to write algorithms on the new global web. Why? The data sets are changing – it’s a moving train. The real-time nature of the web these days is causing a lot of problems for engineers trying to ‘crack the code’ on new search paradigm – it’s search chaos.
Here are some snips from the Google blog post on technology behind their ranking
Search in the last decade has moved from give me what I said to give me what I want. User expectations from search have rightly increased. We work hard to fulfill the expectations of each and every user, and to do that we need to better understand the pages, the queries, and our users. Over the last decade we have pushed the technologies for understanding these three components (of the search process) to completely new dimensions.
Another technology we use in our ranking system is concept identification. Identifying critical concepts in the query allows us to return much more relevant results.
Our clear focus on “best locally relevant results served globally” is reflected in our work on localization. The same query typed in multiple countries may deserve completely different results.
Finally let me briefly mention the latest advance we have made in search: Cross Language Information Retrieval (CLIR). CLIR allows users to first discover information that is not in their language, and then using Google’s translation technology, we make this information accessible.