New work from MIT researchers peers under the hood of an automated fake-news detection system, revealing how machine-learning models catch subtle but consistent differences in the language of factual and false stories. The research also underscores how fake-news detectors should undergo more rigorous testing to be effective for real-world applications.
Popularized as a concept in the United States during the 2016 presidential election, fake news is a form of propaganda created to mislead readers, in order to generate views on websites or steer public opinion.
Almost as quickly as the issue became mainstream, researchers began developing automated fake news detectors — so-called neural networks that “learn” from scores of data to recognize linguistic cues indicative of false articles. Given new articles to assess, these networks can, with fairly high accuracy, separate fact from fiction, in controlled settings.
One issue, however, is the “black box” problem — meaning there’s no telling what linguistic patterns the networks analyze during training. They’re also trained and tested on the same topics, which may limit their potential to generalize to new topics, a necessity for analyzing news across the internet.
In a paper presented at the Conference and Workshop on Neural Information Processing Systems, the researchers tackle both of those issues. They developed a deep-learning model that learns to detect language patterns of fake and real news. Part of their work “cracks open” the black box to find the words and phrases the model captures to make its predictions.
Additionally, they tested their model on a novel topic it didn’t see in training. This approach classifies individual articles based solely on language patterns, which more closely represents a real-world application for news readers. Traditional fake news detectors classify articles based on text combined with source information, such as a Wikipedia page or website.
“In our case, we wanted to understand what was the decision-process of the classifier based only on language, as this can provide insights on what is the language of fake news,” says co-author Xavier Boix, a postdoc in the lab of Tomaso Poggio, the Eugene McDermott Professor in the Department of Brain and Cognitive Sciences (BCS) and director of the Center for Brains, Minds, and Machines (CBMM), a National Science Foundation-funded center housed within the McGovern Institute of Brain Research.
“A key issue with machine learning and artificial intelligence is that you get an answer and don’t know why you got that answer,” says graduate student and first author Nicole O’Brien ’17. “Showing these inner workings takes a first step toward understanding the reliability of deep-learning fake-news detectors.”
The model identifies sets of words that tend to appear more frequently in either real or fake news — some perhaps obvious, others much less so. The findings, the researchers say, points to subtle yet consistent differences in fake news — which favors exaggerations and superlatives — and real news, which leans more toward conservative word choices.
“Fake news is a threat for democracy,” Boix says. “In our lab, our objective isn’t just to push science forward, but also to use technologies to help society. … It would be powerful to have tools for users or companies that could provide an assessment of whether news is fake or not.”
The paper’s other co-authors are Sophia Latessa, an undergraduate student in CBMM; and Georgios Evangelopoulos, a researcher in CBMM, the McGovern Institute, and the Laboratory for Computational and Statistical Learning.
The researchers’ model is a convolutional neural network that trains on a dataset of fake news and real news. For training and testing, the researchers used a popular fake news research dataset, called Kaggle, which contains around 12,000 fake news sample articles from 244 different websites. They also compiled a dataset of real news samples, using more than 2,000 from the New York Times and more than 9,000 from The Guardian.
In training, the model captures the language of an article as “word embeddings,” where words are represented as vectors — basically, arrays of numbers — with words of similar semantic meanings clustered closer together. In doing so, it captures triplets of words as patterns that provide some context — such as, say, a negative comment about a political party. Given a new article, the model scans the text for similar patterns and sends them over a series of layers. A final output layer determines the probability of each pattern: real or fake.
The researchers first trained and tested the model in the traditional way, using the same topics. But they thought this might create an inherent bias in the model, since certain topics are more often the subject of fake or real news. For example, fake news stories are generally more likely to include the words “Trump” and “Clinton.”
“But that’s not what we wanted,” O’Brien says. “That just shows topics that are strongly weighting in fake and real news. … We wanted to find the actual patterns in language that are indicative of those.”
Next, the researchers trained the model on all topics without any mention of the word “Trump,” and tested the model only on samples that had been set aside from the training data and that did contain the word “Trump.” While the traditional approach reached 93-percent accuracy, the second approach reached 87-percent accuracy. This accuracy gap, the researchers say, highlights the importance of using topics held out from the training process, to ensure the model can generalize what it has learned to new topics.
More research needed
To open the black box, the researchers then retraced their steps. Each time the model makes a prediction about a word triplet, a certain part of the model activates, depending on if the triplet is more likely from a real or fake news story. The researchers designed a method to retrace each prediction back to its designated part and then find the exact words that made it activate.
More research is needed to determine how useful this information is to readers, Boix says. In the future, the model could potentially be combined with, say, automated fact-checkers and other tools to give readers an edge in combating misinformation. After some refining, the model could also be the basis of a browser extension or app that alerts readers to potential fake news language.
“If I just give you an article, and highlight those patterns in the article as you’re reading, you could assess if the article is more or less fake,” he says. “It would be kind of like a warning to say, ‘Hey, maybe there is something strange here.’”
“The work touches two very hot research topics: fighting algorithmic bias and explainable AI,” says Preslav Nakov, a professor of electrical engineering and computer science at the University of California at Berkeley, whose work focuses on natural language processing. “In particular, the authors make sure that their approach is not fooled by the prevalence of some topics in fake versus real news. They further show that they can trace back the algorithm’s decision back to specific words in the input article.”
But Nakov also offers a word of caution: it’s difficult to control for many different types of biases in language. For example, the researchers use real news mostly from The New York Times and The Guardian. The next question, he says, is “how do we make sure that a system trained on this dataset would not learn that real news must necessarily follow the writing style of these two specific news outlets?”
Learn more: Peering under the hood of fake-news detectors
The Latest on: Fake news detectors
via Google News
The Latest on: Fake news detectors
- New Detectors At Logan Will Tell You If Your ID Is REAL Or Noton February 26, 2020 at 3:12 pm
A TSA officer at Boston's Logan Airport passed a fake ID through the airport’s new "credential authentication technology" [CAT] system, soliciting an ominous buzzing sound nobody wants to hear when ...
- Top 6 cheap home security devices in 2020on February 25, 2020 at 6:14 am
From professionally installed systems like ADT to DIY solutions like Simplisafe, security systems like can cost an arm and a leg. But if you know just where to look, you can find killer deals on ...
- Only AI can save us from a world of fakes (a world AI is also creating)on February 24, 2020 at 10:29 am
And artificial intelligence (AI) will take it to a whole new level, enabling anyone to create perfect fakes of difficult-to-fake media, like video and audio. The fakers create fakes. The detectors ...
- Fake images can fool autonomous cars, posing risks, Israeli researchers warnon February 23, 2020 at 5:42 pm
“This is not a bug. This is not the result of poor code implementation. This is a fundamental flaw in object detectors that essentially use feature matching for detecting visual objects and were not ...
- UAE launches van to detect drugs, explosives on peopleon February 23, 2020 at 5:28 am
He said, “The van is equipped with a body scanner, conventional luggage scanner and drugs and explosive detection units, besides fake currency and document detectors.” The vehicle is capable ...
- Claims about a fake domb detector earned businessman 'obscene profits'on February 20, 2020 at 4:00 pm
Pictures: Avon and Somerset Police A BRITISH businessman has been sentenced to 10 years in jail for selling fake bomb detectors to the Iraqi government and other countries, by a judge who told him ...
- Pakistan puts press freedom at the core of the struggle for new world orderon February 17, 2020 at 12:05 am
The government justified the rules with the need to combat hate speech, blasphemy, alleged fake news and online harassment of women ... The system would involve the deployment of explosive detectors ...
- Love Island bosses ‘scrap brutal tweet challenge for good‘ after being accused of using ‘fake tweets’on February 11, 2020 at 1:02 pm
The hit ITV2 show’s producers are understood to have binned off the task after being accused of using fake tweets. The savage game ... “We will be looking at lie detectors and other tools used by the ...
- Google releases Assembler to detect doctored imageson February 6, 2020 at 3:22 am
To further help in combating fake news, the tool features two test detectors called StyleGAN and ensemble. StyleGAN uses machine learning to differentiate between images of real people from ...
- Google’s Jigsaw has a new tool that will help journalists flag doctored imageson February 5, 2020 at 5:45 am
Jigsaw has unveiled a tool that can help journalists spot fake images on the Internet ... an amalgamation of various “image manipulation detectors”, each of which can detect specific types ...
via Bing News