Researchers classify Web searches

Apr 10, 2008

Although millions of people use Web search engines, researchers show that – by using relatively simple methods – most queries submitted can be classified into one of three categories.

Jim Jansen, assistant professor in Penn State's College of Information Sciences and Technology, worked with IST undergraduate Danielle Booth and Amanda Spink, Queensland University of Technology, to find that Web search engine users are doing primarily informational, navigational or transactional searching.

Informational searching involves looking for a specific fact or topic, navigational searching seeks to locate a specific Web site and transactional searching looks for information related to buying a particular product or service.

The research was the first published work of its kind done using actual searching data, with the aim of real-time classification. Researchers analyzed more than 1.5 million queries from hundreds of thousands of search engines users. Findings showed that about 80 percent of queries are informational and about 10 percent each are for navigational and transactional purposes.

Jansen and his colleagues arrived at those results by selecting random samples of records and analyzing query length, the order of the query in the session and the search results. These fields helped the team develop an algorithm that classified the searches with a 74-percent accuracy rate.

"Other results have classified comparatively much smaller sets of queries, usually manually," Jansen said. "This research aimed to classify queries automatically.

"Our findings have broad implications for search engines and e-commerce if they can classify the user intent of queries in real time. This is why we wanted a computational undemanding algorithm," Jansen continued. "It proves the 80/20 rule that 80 percent of the cases can be achieved with these clear-cut methods."

The paper "Determining the informational, navigational and transactional intent of Web queries" will appear in the May 2008 issue of Information Processing & Management. The article is currently available online.

The Penn State researcher said he plans to continue this research using a more complex algorithm that will hopefully yield a 90-percent accuracy rate using similar searching criteria.

Source: Penn State

Explore further: Forging a photo is easy, but how do you spot a fake?

add to favorites email to friend print save as pdf

Related Stories

Senate blocks NSA phone records measure (Update)

Nov 19, 2014

The Senate on Tuesday blocked a bill to end bulk collection of Americans' phone records by the National Security Agency, dealing a blow to President Barack Obama's primary proposal to rein in domestic surveillance.

Stanford Libraries unearths the earliest US website

Nov 09, 2014

Some of the earliest pages from the World Wide Web have been restored and are once again browsable, providing a glimpse of how the web once operated. Stanford Libraries has made these pages available with ...

Casting light on the Internet's shadows (and shadowing)

Nov 06, 2014

The specter of a faceless system collecting data from Web users and compiling personal profiles has raised alarms among privacy advocates worldwide. Arvind Narayanan, an assistant professor of computer science at Princeton ...

Next for DARPA: 'Autocomplete' for programmers

Nov 05, 2014

Writing computer programs could become as easy as searching the Internet. A Rice University-led team of software experts has launched an $11 million effort to create a sophisticated tool called PLINY that ...

Recommended for you

Forging a photo is easy, but how do you spot a fake?

Nov 21, 2014

Faking photographs is not a new phenomenon. The Cottingley Fairies seemed convincing to some in 1917, just as the images recently broadcast on Russian television, purporting to be satellite images showin ...

Algorithm, not live committee, performs author ranking

Nov 21, 2014

Thousands of authors' works enter the public domain each year, but only a small number of them end up being widely available. So how to choose the ones taking center-stage? And how well can a machine-learning ...

Professor proposes alternative to 'Turing Test'

Nov 19, 2014

(Phys.org) —A Georgia Tech professor is offering an alternative to the celebrated "Turing Test" to determine whether a machine or computer program exhibits human-level intelligence. The Turing Test - originally ...

Image descriptions from computers show gains

Nov 18, 2014

"Man in black shirt is playing guitar." "Man in blue wetsuit is surfing on wave." "Black and white dog jumps over bar." The picture captions were not written by humans but through software capable of accurately ...

Converting data into knowledge

Nov 17, 2014

When a movie-streaming service recommends a new film you might like, sometimes that recommendation becomes a new favorite; other times, the computer's suggestion really misses the mark. Yisong Yue, assistant ...

User comments : 2

Adjust slider to filter visible comments by rank

Display comments: newest first

Valentiinro
not rated yet Apr 10, 2008
I am wondering where porn fits into this scheme. There is quite a large amount of that on the internet. Informational I suppose?
gopher65
5 / 5 (1) Apr 11, 2008
Definitely Informational.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.