Progress on Personalized Search
October 9, 2013
Some searchers have become excited about algorithmic breakthroughs that promise more personalized results, allowing us to more easily find what we need. A team at North Carolina State University , led by Dr. Kemafor Anyanwu, is advancing the contextual search field with a fresh approach, we learn from “Scaling Up Personalized Query Results for Next Generation of Search Engines” at the University’s Newsroom. Writer Matt Shipman tells us:
“Anyanwu’s team has come up with a way to address the personalized search problem by looking at a user’s ‘ambient query context,’ meaning they look at a user’s most recent searches to help interpret the current search. Specifically, they look beyond the words used in a search to associated concepts to determine the context of a search. . . . And the more recently a concept has been associated with a search, the more weight it is given when ranking results of a new search.”
That makes some sense; if I’ve recently been researching wild animals and search for “jaguar” (the article’s example), it is likely that I would rather not have to sift through results about luxury automobiles. The trade off with personalized search, however, has always been the dramatically increased computational power required to run such a system. The team from NC State has addressed that, too. The article tells us:
“Anyanwu’s research team has now come up with a technique that includes new ways to represent data, new ways to index that data so that it can be accessed efficiently, and a new computing architecture for organizing those indexes. The new technique makes a significant difference.”
How significant? Well, Anyanwu says her team has found the new approach to be about 170 times as fast. That’s nothing to sneeze at, but is it enough to make personalized search feasible? We’ll see. A paper [PDF] on the project is scheduled to be presented at the 2013 IEEE International Conference on Big Data, being held in Santa Clara in early October.
Cynthia Murrell, October 09, 2013
Sponsored by ArnoldIT.com, developer of Augmentext
Comments
One Response to “Progress on Personalized Search”
-
- Subscribe to Beyond Search
Feature archive
News archive
-
Google is doing at least a basic version of this today with Google Now. When I ask my phone “how old is Tom Brady” the GN voice tells me he is 36 years old, when I ask “what team does he play for”, the GN voice tells me that Tom Brady plays for the NE Patriots. It remembered “who” from the initial query. -FB