The Stanly News and Press (Albemarle, NC)

State & National News

September 20, 2013

NCSU Study: Scaling Up Personalized Query Results for Next Generation of Search Engines

Friday, September 20, 2013 — North Carolina State University researchers have developed a way for search engines to provide users with more accurate, personalized search results. The challenge in the past has been how to scale this approach up so that it doesn’t consume massive computer resources. Now the researchers have devised a technique for implementing personalized searches that is more than 100 times more efficient than previous approaches.

 

At issue is how search engines handle complex or confusing queries. For example, if a user is searching for faculty members who do research on financial informatics, that user wants a list of relevant webpages from faculty, not the pages of graduate students mentioning faculty or news stories that use those terms. That’s a complex search.

 

“Similarly, when searches are ambiguous with multiple possible interpretations, traditional search engines use impersonal techniques. For example, if a user searches for the term ‘jaguar speed,’ the user could be looking for information on the Jaguar supercomputer, the jungle cat or the car,” says Dr. Kemafor Anyanwu, an assistant professor of computer science at NC State and senior author of a paper on the research. “At any given time, the same person may want information on any of those things, so profiling the user isn’t necessarily very helpful.”

 

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. So, if a user’s previous search contained the word “conservation” it would be associated with concepts likes “animals” or “wildlife” and even “zoos.” Then, a subsequent search for “jaguar speed” would push results about the jungle cat higher up in the results – and not the automobile or supercomputer. 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.

 

Search engines have also tried to identify patterns in user clicking behavior on search results to identify the most probable user intent for a search. However, such techniques are impersonal and are applied on a global basis. So, if the most frequent click pattern for a set of keywords is in a particular context, then that context becomes the context associated with queries for most or all users – even if your recent search history indicates that your query context is about jungle cats.

 

“What we are doing is different,” Anyanwu says. “We are identifying the context of search terms for individual users in real time and using that to determine a user’s intention for a specific query at a specific time. This allows us to deal more effectively with more complex searches than traditional search engines. Such searches are becoming more prevalent as people now use the Web as a key knowledge base supporting different types of tasks.”

 

While Anyanwu and her team developed a context-aware personalized search technique over a year ago, the challenge has been how to scale this approach up. “Because running an ambient context program for every user would take an enormous amount of computing resources, and that is not feasible,” Anyanwu says.

 

However, 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.

 

“Our new indexing and search computing architecture allows us to support personalized search for about 2,900 concurrent users using an 8GB machine, whereas an earlier approach supported only 17 concurrent users. This makes the concept more practical, and moves us closer to the next generation of search engines,” Anyanwu says.

 

The paper, “Personalizing Search: A Case for Scaling Concurrency in Multi-Tenant Semantic Web Search Systems,” will be presented at the 2013 IEEE International Conference on Big Data being held Oct. 6-9 in Santa Clara, Calif. Lead author of the paper is Dr. Haizhou Fu, a former Ph.D. student at NC State. The paper was co-authored by Hyeongsik Kim, a Ph.D. student at NC State. The research was supported by the National Science Foundation.

 

1
Text Only
State & National News
  • Why Facebook is getting into the banking game

    Who would want to use Facebook as a bank? That's the question that immediately arises from news that the social network intends to get into the electronic money business.

    April 15, 2014

  • E-Cigarettes target youth with festivals, lawmakers say

    WASHINGTON - The findings, in a survey released Monday by members of Congress, should prod U.S. regulators to curb the industry, the lawmakers said. While e-cigarettes currently are unregulated, the Food and Drug Administration is working on a plan that would extend its tobacco oversight to the products.

    April 15, 2014

  • Search teams will send unmanned sub to look for missing Malaysian airliner

    Teams searching for a missing Malaysian airliner are planning for the first time to send an unmanned submarine into the depths of the Indian Ocean to look for wreckage, an Australian official leading the multi-nation search said Monday.

    April 15, 2014

  • Millions of Android phones, tablets vulnerable to Heartbleed bug

    SAN FRANCISCO - Millions of smartphones and tablets running Google's Android operating system have the Heartbleed software bug, in a sign of how broadly the flaw extends beyond the Web and into consumer devices.

    April 13, 2014

  • DayCareCosts.jpg Day care's cost can exceed college tuition in some states

    Most parents will deal with an even larger kid-related expense long before college, and it's a cost that very few of them are as prepared for: day care.

    April 12, 2014 1 Photo

  • Stepping forward: The real Colbert

    Letterman changed the late-night TV game between his run on NBC's "Late Night" and starting the "Late Show" franchise in 1993. And while it's tough to replace a pop-culture icon, Colbert, in terms of pedigree and sense of humor, makes the most sense.

    April 12, 2014

  • Boston doctors can now prescribe you a bike

    The City of Boston this week is rolling out a new program that's whimsically known as "Prescribe-a-Bike." Part medicine, part welfare, the initiative allows doctors at Boston Medical Center to write "prescriptions" for low-income patients to get yearlong memberships to Hubway, the city's bike-share system, for only $5.

    April 12, 2014

  • Fast, cheap test can help save lives of many babies

    As Easley did more research into her daughter's death, she learned that a pilot program had started just months earlier at Holy Cross Hospital in Silver Spring, Md. (Easley had delivered at a different hospital in the Washington area.) The program's goal was to screen every newborn with a simple pulse oximeter test that can help detect heart problems such as Veronica's, allowing doctors to respond.

    April 10, 2014

  • 140407_GT_OUT_Forster_1.jpg Revolutionary War flag could fetch millions at auction

    MANCHESTER, MASS. - An iconic piece of history from the Revolutionary War is up for auction through Doyle New York, an auction and appraising company in New York City.

    April 10, 2014 1 Photo

  • 2012_Mazda6_--_NHTSA.jpg Brakes, steering and...spiders? What's behind the latest auto recalls

    11 million vehicles have already been recalled in 2014 for everything from power steering failure to vulnerability to spider attack.

    Check out the full list of 2014 recalls.

    April 10, 2014 1 Photo

House Ads
Seasonal Content