Dealing with misinformation in the digital age is a complex problem. Not only does misinformation have to be identified, tagged, and corrected, but the intent of those responsible for making the claim should also be distinguished. A person may unknowingly spread misinformation, or just be giving their opinion on an issue even though it is later reported as fact. Recently, a team of AI researchers and engineers at Dartmouth created a framework that can be used to derive opinion from “fake news” reports.
As ScienceDaily reports, the Dartmouth team’s study was recently published in the Journal of Experimental & Theoretical Artificial Intelligence. While previous studies have attempted to identify fake news and fight deception, this might be the first study that aimed to identify the intent of the speaker in a news piece. While a true story can be twisted into various deceptive forms, it’s important to distinguish whether or not deception was intended. The research team argues that intent matters when considering misinformation, as deception is only possible if there was intent to mislead. If an individual didn’t realize they were spreading misinformation or if they were just giving their opinion, there can’t be deception.
Eugene Santos Jr., an engineering professor at Dartmouth’s Thayer School of Engineering, explained to ScienceDaily why their model attempts to distinguish deceptive intent:
“Deceptive intent to mislead listeners on purpose poses a much larger threat than unintentional mistakes. To the best of our knowledge, our algorithm is the only method that detects deception and at the same time discriminates malicious acts from benign acts.”
In order to construct their model, the research team analyzed the features of deceptive reasoning. The resulting algorithm could distinguish intent to deceive from other forms of communication by focusing on discrepancies between a person’s past arguments and their current statements. The model constructed by the research team needs large amounts of data that can be used to measure how a person deviates from past arguments. The training data the team used to train their model consisted of data taken from a survey of opinions on controversial topics. Over 100 people gave their opinion on these controversial issues. Data was also pulled from reviews of 20 different hotels, consisting of 400 fictitious reviews and 800 real reviews.
According to Santo, the framework developed by the researchers could be refined and applied by news organizations and readers, in order to let them analyze the content of “fake news” articles. Readers could examine articles for the presence of opinions and determine for themselves if a logical argument has been used. Santos also said that the team wants to examine the impact of misinformation and the ripple effects that it has.
Popular culture often depicts non-verbal behaviors like facial expressions as indicators that someone is lying, but the authors of the study note that these behavioral hints aren’t always reliable indicators of lying. Deqing Li, co-author on the paper, explained that their research found that models based on reasoning intent are better indicators of lying than behavioral and verbal differences. Li explained that reasoning intent models “are better at distinguishing intentional lies from other types of information distortion”.
The work of the Dartmouth researchers isn’t the only recent advancement when it comes to fighting misinformation with AI. News articles with clickbait titles often mask misinformation. For example, they often imply one thing happened when another event actually occurred.
As reported by AINews, a team of researchers from both Arizona State University and Penn State University collaborated in order to create an AI that could detect clickbait. The researchers asked people to write their own clickbait headlines and also wrote a program to generate clickbait headlines. Both forms of headlines were then used to train a model that could effectively detect clickbait headlines, regardless of whether they were written by machines or people.
According to the researchers, their algorithm was around 14.5% more accurate, when it came to detecting clickbait titles than other AIs had been in the past. The lead researcher on the project and associate professor at the College of Information Sciences and Technology at Penn State, Dongwon Lee, explained how their experiment demonstrates the utility of generating data with an AI and feeding it back into a training pipeline.
“This result is quite interesting as we successfully demonstrated that machine-generated clickbait training data can be fed back into the training pipeline to train a wide variety of machine learning models to have improved performance,” explained Lee.
Artificial Intelligence Algorithm Used to Predict Agriculture Yield
It is predicted that the precision agriculture market will reach $12.9 billion by 2027. With this increase, there is a need for sophisticated data-analysis solutions that are capable of guiding management decisions in real-time. A new methodology has been developed by an interdisciplinary group at the University of Illinois, and it aims to efficiently and accurately process precision agricultural data.
Nicolas Martin is an assistant professor in the Department of Crop Sciences at Illinois and co-author of the study.
“We’re trying to change how people run agronomic research. Instead of establishing a small field plot, running statistics, and publishing the means, what we’re trying to do involves the farmer far more directly. We are running experiments with farmers’ machinery in their own fields. We can detect site-specific responses to different inputs. And we can see whether there’s a response in different parts of the field,” he says.
“We developed methodology using deep learning to generate yield predictions. It incorporates information from different topographic variables, soil electroconductivity, as well as nitrogen and seed rate treatments we applied throughout nine Midwestern corn fields.”
The team used 2017 and 2018 data from the Data Intensive Farm Management project to help develop their approach. In that project, seeds and nitrogen fertilizer were applied at different rates across 226 fields. Those fields were in different areas of the world, including the Midwest, Brazil, Argentina, and South Africa. High-resolution satellite images were provided by PlanetLab, and they were paired with on-ground measurements in order to predict yield.
The fields were digitally separated into 5-meter squares. The computer was given data on soil, elevation, nitrogen application rate, and seed rate for each square, and it then began to learn how the yield in that square is determined by the interaction of the factors.
In order to complete their analysis, the researchers relied on a convolutional neural network (CNN). A CNN is a type of machine learning or artificial intelligence. While some types of machine learning get computers to add new data into existing patterns, convolutional neural networks do not take existing patterns into account. CNN’s look at data and learn the patterns that are responsible for organizing it, and it works in a similar way to how humans organize information through neural networks within the brain. The CNN approach was able to predict yield with a high accuracy rate, and it was compared to other machine learning algorithms and traditional statistical techniques.
“We don’t really know what is causing differences in yield responses to inputs across a field. Sometimes people have an idea that a certain spot should respond really strongly to nitrogen and it doesn’t, or vice versa. The CNN can pick up on hidden patterns that may be causing a response,” Martin says. “And when we compared several methods, we found out that the CNN was working very well to explain yield variation.”
The use of artificial intelligence to analyze data from precision agriculture is a new field, but it is one that is growing. Agriculture is one of the major industries that will be drastically changed by artificial intelligence, and the use of it is continuing to increase. According to Martin, this experiment is just the start of CNN’s being used in a variety of different applications.
“Eventually, we could use it to come up with optimum recommendations for a given combination of inputs and site constraints.”
Deep Learning Used to Find Disease-Related Genes
A new study led by researchers at Linköping University demonstrates how an artificial neural network (ANN) can reveal large amounts of gene expression data, and it can lead to the discovery of groups of disease-related genes. The study was published in Nature Communications, and the scientists want the method to be applied within precision medicine and individualized treatment.
Scientists are currently developing maps of biological networks that are based on how different proteins or genes interact with each other. The new study involves the use of artificial intelligence (AI) in order to find out if biological networks can be discovered through the use of deep learning. Artificial neural networks, which are trained by experimental data in the process of deep learning, are able to find patterns within massive amounts of complex data. Because of this, they are often used in applications such as image recognition. Even with its seemingly enormous potential, the use of this machine learning method has been limited within biological research.
Sanjiv Dwivedi is a postdoc in the Department of Physics, Chemistry and Biology (IFM) at Linköping University.
“We have for the first time used deep learning to find disease-related genes. This is a very powerful method in the analysis of huge amounts of biological information, or ‘big data’,” says Dwivedi.
The scientists relied on a large database with information regarding the expression patterns of 20,000 genes in a large number of people. The artificial neural network was not told which gene expression patterns were from people with diseases, or which ones were from healthy individuals. The AI model was then trained to find patterns of gene expression.
One of the mysteries surrounding machine learning is that it is currently impossible to see how an artificial neural network gets to its final result. It is only possible to see the information that goes in and the information that is produced, but everything that happens in-between consists of several layers of mathematically processed information. These inner workings of an artificial neural network are not yet able to be deciphered. The scientists wanted to know if there were any similarities between the designs of the neural network and the familiar biological networks.
Mike Gustafsson is a senior lecturer at IFM and leads the study.
“When we analysed our neural network, it turned out that the first hidden layer represented to a large extent interactions between various proteins. Deeper in the model, in contrast, on the third level, we found groups of different cell types. It’s extremely interesting that this type of biologically relevant grouping is automatically produced, given that our network has started from unclassified gene expression data,” says Gustafsson.
The scientists then wanted to know if their model of gene expression was capable of being used to determine which gene expression patterns are associated with disease and which are normal. They were able to confirm that the model can discover relative patterns that agree with biological mechanisms in the body. Another discovery was that the artificial neural network could possibly discover brand new patterns since it was trained with unclassified data. The researchers will now investigate previously unknown patterns and whether they are relevant within biology.
“We believe that the key to progress in the field is to understand the neural network. This can teach us new things about biological contexts, such as diseases in which many factors interact. And we believe that our method gives models that are easier to generalise and that can be used for many different types of biological information,” says Gustafsson.
Through collaborations with medical researchers, Gustafsson hopes to apply the method in precision medicine. This could help determine which specific types of medicine patients should receive.
The study was financially supported by the Swedish Foundation for Strategic Research (SSF) and the Swedish Research Council.
Deep Learning System Can Accurately Predict Extreme Weather
Engineers at Rice University have developed a deep learning system that is capable of accurately predicting extreme weather events up to five days in advance. The system, which taught itself, only requires minimal information about current weather conditions in order to make the predictions.
Part of the system’s training involves examining hundreds of pairs of maps, and each map indicates surface temperatures and air pressures at five-kilometers height. Those conditions are shown several days apart. The training also presents scenarios that produced extreme weather, such as hot and cold spells that can cause heat waves and winter storms. Upon completing the training, the deep learning system was able to make five-day forecasts of extreme weather based on maps it had not previously seen, with an accuracy rate of 85%.
According to Pedram Hassanzadeh, co-author of the study which was published online in the American Geophysical Union’s Journal of Advances in Modeling Earth Systems, the system could be used as a tool and act as an early warning for weather forecasters. It will be especially useful for learning more about certain atmospheric conditions that cause extreme weather scenarios.
Because of the invention of computer-based numerical weather prediction (NWP) in the 1950s, day-to-day weather forecasts have continued to improve. However, NWP is not able to make reliable predictions about extreme weather events, such as heat waves.
“It may be that we need faster supercomputers to solve the governing equations of the numerical weather prediction models at higher resolutions,” said Hassanzadeh, an assistant professor of mechanical engineering and of Earth, environmental and planetary sciences at Rice University. “But because we don’t fully understand the physics and precursor conditions of extreme-causing weather patterns, it’s also possible that the equations aren’t fully accurate, and they won’t produce better forecasts, no matter how much computing power we put in.”
In 2017, Hassanzadeh was joined by study co-authors and graduate students Ashesh Chattopadhyay and Ebrahim Nabizadeh. Together, they set out on a different path.
“When you get these heat waves or cold spells, if you look at the weather map, you are often going to see some weird behavior in the jet stream, abnormal things like large waves or a big high-pressure system that is not moving at all,” Hassanzadeh said. “It seemed like this was a pattern recognition problem. So we decided to try to reformulate extreme weather forecasting as a pattern-recognition problem rather than a numerical problem.”
“We decided to train our model by showing it a lot of pressure patterns in the five kilometers above the Earth, and telling it, for each one, ‘This one didn’t cause extreme weather. This one caused a heat wave in California. This one didn’t cause anything. This one caused a cold spell in the Northeast,'” Hassanzadeh continued. “Not anything specific like Houston versus Dallas, but more of a sense of the regional area.”
Prior to computers, analog forecasting was used for weather prediction. It was done in a very similar way to the new system, but it was humans instead of computers.
“One way prediction was done before computers is they would look at the pressure system pattern today, and then go to a catalog of previous patterns and compare and try to find an analog, a closely similar pattern,” Hassanzadeh said. “If that one led to rain over France after three days, the forecast would be for rain in France.”
Now, neural networks can learn on their own and do not necessarily need to rely on humans to find connections.
“It didn’t matter that we don’t fully understand the precursors because the neural network learned to find those connections itself,” Hassanzadeh said. “It learned which patterns were critical for extreme weather, and it used those to find the best analog.”
To test their concept, the team relied on data taken from realistic computer simulations. They originally reported early results with a convolutional neural network, but the team then shifted towards capsule neural networks. Convolutional neural networks are not able to recognize relative spatial relationships, but capsule neural networks can. These relative spatial relationships are important when it comes to the evolution of weather patterns.
“The relative positions of pressure patterns, the highs and lows you see on weather maps, are the key factor in determining how weather evolves,” Hassanzadeh said.
Capsule neural networks also require less training data than convolutional neural networks.
The team will continue to work on the system in order for it to be capable of being used in operational forecasting, but Hassanzadeh hopes that it eventually will lead to more accurate forecasts for extreme weather.
“We are not suggesting that at the end of the day this is going to replace NWP,” he said. “But this might be a useful guide for NWP. Computationally, this could be a super cheap way to provide some guidance, an early warning, that allows you to focus NWP resources specifically where extreme weather is likely.”
“We want to leverage ideas from explainable AI (artificial intelligence) to interpret what the neural network is doing,” he said. “This might help us identify the precursors to extreme-causing weather patterns and improve our understanding of their physics.”