An algorithm-based system that identifies telltale linguistic cues in fake news stories could provide news aggregator and social media sites like Google News with a new weapon in the fight against misinformation.
The University of Michigan researchers who developed the system have demonstrated that it’s comparable to and sometimes better than humans at correctly identifying fake news stories.
In a recent study, it successfully found fakes up to 76 percent of the time, compared to a human success rate of 70 percent. In addition, their linguistic analysis approach could be used to identify fake news articles that are too new to be debunked by cross-referencing their facts with other stories.
Rada Mihalcea, the U-M computer science and engineering professor behind the project, said an automated solution could be an important tool for sites that are struggling to deal with an onslaught of fake news stories, often created to generate clicks or to manipulate public opinion.
Catching fake stories before they have real consequences can be difficult, as aggregator and social media sites today rely heavily on human editors who often can’t keep up with the influx of news. In addition, current debunking techniques often depend on external verification of facts, which can be difficult with the newest stories. Often, by the time a story is proven a fake, the damage has already been done.
Linguistic analysis takes a different approach, analyzing quantifiable attributes like grammatical structure, word choice, punctuation and complexity. It works faster than humans and it can be used with a variety of different news types.
“You can imagine any number of applications for this on the front or back end of a news or social media site,” Mihalcea said. “It could provide users with an estimate of the trustworthiness of individual stories or a whole news site. Or it could be a first line of defense on the back end of a news site, flagging suspicious stories for further review. A 76 percent success rate leaves a fairly large margin of error, but it can still provide valuable insight when it’s used alongside humans.”
Linguistic algorithms that analyze written speech are fairly common today, Mihalcea said. The challenge to building a fake news detector lies not in building the algorithm itself, but in finding the right data with which to train that algorithm.
Fake news appears and disappears quickly, which makes it difficult to collect. It also comes in many genres, further complicating the collection process. Satirical news, for example, is easy to collect, but its use of irony and absurdity make it less useful for training an algorithm to detect fake news that’s meant to mislead.
Ultimately, Mihalcea’s team created its own data, crowdsourcing an online team that reverse-engineered verified genuine news stories into fakes. This is how most actual fake news is created, Mihalcea said, by individuals who quickly write them in return for a monetary reward.
Study participants, recruited with the help of Amazon Mechanical Turk, were paid to turn short, actual news stories into similar but fake news items, mimicking the journalistic style of the articles. At the end of the process, the research team had a dataset of 500 real and fake news stories.
They then fed these labeled pairs of stories to an algorithm that performed a linguistic analysis, teaching itself distinguish between real and fake news. Finally, the team turned the algorithms to a dataset of real and fake news pulled directly from the web, netting the 76 percent success rate.
The details of the new system and the dataset that the team used to build it are freely available, and Mihalcea says they could be used by news sites or other entities to build their own fake news detection systems. She says that future systems could be further honed by incorporating metadata such as the links and comments associated with a given online news item.
The Latest on: Fake news
via Google News
The Latest on: Fake news
- Iowa Man Arrested After Using Fake 'McLovin' ID Card to Access Bar While Underageon October 15, 2019 at 1:31 am
A 20-year-old Iowa man was taken into custody last week after allegedly using a fake Hawaii ID with the name "McLovin" to access a city bar. Daniel Alfredo Burleson, 20, of Des Moines, was arrested by ...
- Fake videos could be the next big problem in the 2020 electionson October 15, 2019 at 12:30 am
Fake news was a big problem for the 2016 election. "Deepfake" videos could be an even bigger problem in 2020. Deepfake technology can be used to create videos that seem to show politicians saying ...
- Fake video of Trump shooting media doesn't violate YouTube's rules, company tells CNNon October 14, 2019 at 2:42 pm
A fake video that depicts in extremely graphic fashion President Trump attacking and shooting his critics and media outlets does not violate YouTube's policies against content that incites violence ...
- Fake Trump shooting video traces back to a prolific creator and a fervent communityon October 14, 2019 at 2:38 pm
About 18 months before a violent video of a fake President Donald Trump superimposed on a violent action movie became national news Monday, a video creator who goes by TheGeekzTeam uploaded a similar ...
- A pro-Trump group showed a video of a fake Trump shooting and brutally stabbing journalists and political foes at a conference for his supporterson October 14, 2019 at 1:44 pm
The clip shows a fake "Trump" attacking reporters, shooting them at point-blank range, and smiling at the massacre.
- Outcry after Trump fails to condemn fake video of him shooting opponentson October 14, 2019 at 1:41 pm
In the edited video, Trump’s face is digitally superimposed on to Firth’s body, and he is depicted shooting, stabbing and attacking adversaries in the “Church of Fake News”. It includes a scene of him ...
- The conference held at a Trump resort featuring a fake Trump shooting video is emblematic of the president's ties to dubious right-wing groupson October 14, 2019 at 12:17 pm
Donald Trump's presidency has opened the door for far-right groups like American Priority to infiltrate mainstream conservatism in the US.
- White House Distances Itself From Violent Fake Video Targeting Media And Criticson October 14, 2019 at 9:34 am
In the parody video, Trump's head is superimposed on the body of a man opening fire inside the "Church of Fake News," according to the New York Times who first reported the playing of the video. The ...
- Criticism grows after fake video of Trump massacring media, opponents shown at his Miami resorton October 14, 2019 at 8:48 am
At the center of the bloody rampage unfolding in the "Church of Fake News" is a man dressed in a dark pinstripe suit. President Trump's head is superimposed on his body. The graphic images are from a ...
- Video of a Fake Trump Massacring Media and Critics Shown at Pro-Trump Eventon October 14, 2019 at 8:27 am
The first person a fake version of Donald Trump kills after entering the “Church of Fake News” is a fake version of Peter Fonda, who once tweeted something terrible about Barron Trump. Then he turns ...
via Bing News