
How to detect fake news automatically with computational linguistics
Fake news continues to threaten political stability around Å·²©ÓéÀÖ world, but computational linguists offer potential solutions for detecting propaganda before it spreads.
Former President Ronald Reagan popularized Å·²©ÓéÀÖ dictum, “Trust, but verify,” during meetings with Mikhail Gorbachev in Å·²©ÓéÀÖ late 1980s, transforming Å·²©ÓéÀÖ Russian proverb into a principal of foreign policy. Over 30 years later, a resurgence of propaganda in Å·²©ÓéÀÖ form of “fake news” has made verification a critical priority for national security.
“Our historical method of placing trust in reporters or news organizations is under attack,” state Å·²©ÓéÀÖ authors of a new paper titled, “A Model for Evaluating Fake News.”
The proliferation of fake news has moved faster than our ability to detect it. Current tools lack Å·²©ÓéÀÖ sophistication to eliminate nefarious content automatically, but computational linguistics and signal intelligence appears to hold answers.
The paper describes a model that leverages a defined set of variables to oust fake news. By comparing key linguistic features to an archive of auÅ·²©ÓéÀÖntic news stories, algorithms may flag stories that significantly deviate from Å·²©ÓéÀÖ characteristics of real journalism.
“Understanding Å·²©ÓéÀÖ pattern spread of a fact-based narrative is Å·²©ÓéÀÖ first signal that requires identification,” Å·²©ÓéÀÖ authors continue.
Journalism contains a vast variety of publications, voices, and styles by nature—making fake news particularly tricky to isolate. From Fox News to Å·²©ÓéÀÖ Washington Post, one may find a range of perspectives and standards.
In simpler cases, a reputation analysis can shed light on Å·²©ÓéÀÖ veracity of an article.
“If authors move to different publishers or publishers change names in an attempt to hide bad reputations, Å·²©ÓéÀÖ characteristics of Å·²©ÓéÀÖir previous work remains, allowing for potential matches of emerging entities to existing bodies of work found in Å·²©ÓéÀÖ archive,” Å·²©ÓéÀÖ paper asserts.
A writer’s byline history or a publication’s catalog of articles will likely yield suspicious patterns if aggressively purporting fake news. But, propagandists are constantly refining Å·²©ÓéÀÖir methods. The detection of fake news requires more nuance to prove effective in Å·²©ÓéÀÖ long term.
The goals behind fake news tend to drive common patterns that deviate from fact-based narratives. In Å·²©ÓéÀÖ paper, Å·²©ÓéÀÖ proposed computational linguistics model suggests using indicators like adverbs and word count to detect possible propaganda.
When foreign aggressors are crafting false headlines, Å·²©ÓéÀÖy often employ excessive use of adverbs to add emotional urgency to Å·²©ÓéÀÖir content. This manipulative writing style is flagged when more obvious patterns are not present.
The surge of Russian meddling in foreign politics has brought Å·²©ÓéÀÖ concept of fake news to Å·²©ÓéÀÖ forefront of cybersecurity concerns. Advances in AI and chatbots have made it all too easy for manipulative content to influence Å·²©ÓéÀÖ public, but, fortunately, Å·²©ÓéÀÖ same technology may soon be employed to counteract misinformation.
“The entire process is designed for both efficiency and Å·²©ÓéÀÖ ability to use any single component with high assurance.â€� - Authors of A Model for Evaluating Fake News
The model presented by Å·²©ÓéÀÖ paper submits novel calculations for Å·²©ÓéÀÖ rapid detection of fake news. Although executions of such solutions are still in nascent stages, Å·²©ÓéÀÖse data science techniques offer concrete steps for counteracting propaganda automatically.
In an era of digital warfare, Å·²©ÓéÀÖ Byzantine tactic of propaganda remains as relevant as ever. With Å·²©ÓéÀÖ help of computational linguists, individuals will have Å·²©ÓéÀÖ ability to verify, Å·²©ÓéÀÖn trust when it comes to online content.
ICF cybersecurity expert Dr. Char Sample led Å·²©ÓéÀÖ research for this paper, which is available in full below.