Algorithm detects Canadian politicians’ spin
by Stu Hutson | NewScientist.com
With the most fiercely fought Canadian election in more than a decade taking place on Monday, the crossfire of political rhetoric between the incumbent prime minister and his Conservative Party challenger is becoming heated – but which one is more trustworthy?
According to a new computer algorithm, Prime Minister Paul Martin, of the Liberal Party, spins the subject matter of his speeches dramatically more than Conservative Party leader, Stephen Harper, and the New Democratic Party leader, Jack Layton.
Spin, in this case, is defined as “text or speech where the apparent meaning is not the true belief of the person saying or writing it”, says the algorithm’s developer, David Skillicorn at Queen’s University in Ontario, Canada.
He and his team analyzed the usage patterns of 88 deception-linked words within the text of recent campaign speeches from the political leaders. They then determined the frequency of these patterns in each speech, and averaged that number over all of that candidate’s speeches. Martin received a ranking of 124, while Harper and Layton scored 73 and 88, respectively.
“I think it’s expected that any party in power is going to use spin more than the challenging party,” Skillicorn says. “They have a track record to defend.”
Tarnished record With a solid run of 14 years as the dominant party in Canada, the Liberal Party has a long record – one which has been tarnished in the past year by accusations of illegal donations and kickbacks. Many political experts expect the conservatives, who have a solid lead in the polls, to oust the liberal party this election.
“The guy who’s doing the most tap-dancing is the guy who’s under the spotlight,” said John Wright, senior vice president of the polling company Ipsos Reid. “The pressure is going to show.”
Conservative parliament members, such as Jason Kenney, point to the analysis as proof of their leader’s honesty. “People used to think he’s boring, but now they recognize that he’s a straight shooter without the spin.”
But Liberal Party spokesman Ken Polk disagrees: “If that is what the algorithm shows, I think it needs quite a bit of work,” he says.
Interrogator tactics The computer algorithm is based on a psychological model constructed by James Pennebaker at the University of Texas, Austin, US. While studying the lying and truth-telling of hundreds of test subjects, he uncovered patterns linked to deception, such as the decreased use of personal pronouns – such as I, we, me, us – and exception words, such as “however” and “unless”.
The patterns are probably of subconscious origin, he said, much like the physical cues – such as pupil dilation or changes in breathing – which interrogators use to tell when a subject is being untruthful.
Skillicorn decided to apply the technique to the presidential speeches after using it to investigate the text of emails sent between Enron Corporation executives before the company’s infamous bankruptcy in 2001.
He admits that the algorithm is still a work in progress, but “with this much of a difference, I think the results are still pretty clear”.
Posted Sat Jan 21st, 2006
