Sad! Drifting word meanings may be creating two different political languagesPosted on July 31, 2017
UNIVERSITY PARK, Pa. — If the current political discourse sounds a little like people are speaking two different languages, Penn State psychologists, who studied political rhetoric over the past three presidential elections, say that may be close to the case, semantically speaking.
In a series of studies, the researchers found a split between the same words presidential candidates from the nation’s two major political parties used and what those words mean. This semantic divide appears to be growing, they added, which may continue to make the possibility of dialogue difficult, if not impossible.
“This work was actually finished last year before the 2016 elections and we were struck by how different the rhetoric was between these different candidates,” said Ping Li, professor of psychology and associate director of the Institute for CyberScience. “In a lot of ways, it’s worse than speaking two different languages. If, for example, I speak Chinese and you don’t, you have no idea what I’m saying. But, if we’re both speaking English and you think you know what I am saying, but don’t get what I actually mean, or worse, think it means something different, it can be really confusing.”
The researchers examined how presidential candidates used words together — word association — in speeches and debates since 1999 to help determine the meaning of those words in the minds of the candidates. For example, when the word “table” appears in text together with the word “chair,” it provides meaning — or context — that the speaker is referring to a type of furniture, Li said. However, if “table” is used in a sentence with terms such as “town council” and “regulation,” for example, “table” could mean a type of legislative action.
In politics, context can be subtler and more complicated, according to the researchers, who report their findings in Behavior Research Methods, available online now.
“For example, if I use the word ‘security,’ that can mean a lot of different things,” he said. “Maybe I am referring to job security, or cyber-security, military security, or some other type of meaning for the word. Also, not only do the words in political speeches reflect different ideologies and ideas of the parties, but they can reflect the times of when the speech was made, so the meaning can change over time.”
In the most recent presidential election, the researchers said words, such as “deal” and “education,” provided not just a glimpse into how different the political rhetoric was between then-candidates Donald Trump and Hillary Clinton, but also suggests differences between their beliefs.
“In Donald Trump’s speeches, as a business person, he would apply the word ‘deal’ to almost anything,” said Li, who served as the paper’s lead author. “Of course, ‘deal’ is often associated with business, but, in his speeches, he also associated it with family and education, which would not traditionally be grouped together. So, this goes back to how word association can reflect attitudes and beliefs, as also shown in a recent Science paper by Aylin Caliskan and colleagues.”
Clinton, on the other hand, would more often associate the word “education” with women and family, he said.
“In this case, ‘education’ became an issue of equality and allowing everyone access to education,” said Li, who worked with Benjamin Schloss, a graduate student in cognitive psychology, and Jake Follmer, a graduate student in educational psychology.
The researchers compiled a list of 213 single words and 397 word phrases, including 136 politically charged words — such as “minority,” “spending” and “justice” — used by American political parties. They then used an artificial neural network algorithm to statistically examine how often words appear together in a sentence, or speech.
The researchers also found that political word association has changed over time.
“We charted word meaning changes over time between parties,” said Li. “What you see is that the parties have become farther and farther apart as time goes on. In other words, for the same word, people tend to associate different words for them and, hence, convey different meanings.”
In a follow-up study, the researchers were able to examine the word associations of a group of 324 participants and, by using machine-learning algorithms, predict their political leanings and what party they belonged to, as well as which candidate they were likely to vote for in the presidential elections.
“We were able to predict voters’ reported political affiliations with a relatively high degree of accuracy simply based on the way they organized a list of 50 political concepts, that is, how they grouped these concepts,” said Li. “This also suggests the complex interdependence of language, speech and culture.”
In the future, Li said the researchers may try to provide a more detailed picture of these interdependences by looking into more political concepts and documents from a larger pool of candidates and with more sophisticated computational methods.
This article originally appeared on Penn State News. Read the original here.
- Featured Researcher: Nick Tusay
- Multi-institutional team to use AI to evaluate social, behavioral science claims
- NSF invests in cyberinfrastructure institute to harness cosmic data
- Center for Immersive Experiences set to debut, serving researchers and students
- Distant Suns, Distant Worlds
- CyberScience Seminar: Researcher to discuss how AI can help people avoid adverse drug interactions
- AI could offer warnings about serious side effects of drug-drug interactions
- Taking RTKI drugs during radiotherapy may not aid survival, worsens side effects
- Cost-effective cloud research computing options now available for researchers
- Costs of natural disasters are increasing at the high end
- Model helps choose wind farm locations, predicts output
- Virus may jump species through ‘rock-and-roll’ motion with receptors
- Researchers seek to revolutionize catalyst design with machine learning
- Resilient Resumes team places third in Nittany AI Challenge
- ‘AI in Action’: Machine learning may help scientists explore deep sleep
- Clickbait Secrets Exposed! Humans and AI team up to improve clickbait detection
- Focusing computational power for more accurate, efficient weather forecasts
- How many Earth-like planets are around sun-like stars?
- Professor receives NSF grant to model cell disorder in heart
- SMH! Brains trained on e-devices may struggle to understand scientific info
- Whole genome sequencing may help officials get a handle on disease outbreaks
- New tool could reduce security analysts’ workloads by automating data triage
- Careful analysis of volcano’s plumbing system may give tips on pending eruptions
- Reducing farm greenhouse gas emissions may plant the seed for a cooler planet
- Using artificial intelligence to detect discrimination
- Four ways scholars say we can cut the chances of nasty satellite data surprises
- Game theory shows why stigmatization may not make sense in modern society
- Older adults can serve communities as engines of everyday innovation
- Pig-Pen effect: Mixing skin oil and ozone can produce a personal pollution cloud
- Researchers find genes that could help create more resilient chickens
- Despite dire predictions, levels of social support remain steady in the U.S.
- For many, friends and family, not doctors, serve as a gateway to opioid misuse
- New algorithm may help people store more pictures, share videos faster
- Head named for Ken and Mary Alice Lindquist Department of Nuclear Engineering
- Scientific evidence boosts action for activists, decreases action for scientists
- People explore options, then selectively represent good options to make difficult decisions
- Map reveals that lynching extended far beyond the deep South
- Gravitational forces in protoplanetary disks push super-Earths close to stars
- Supercomputer cluster donation helps turn high school class into climate science research lab
- Believing machines can out-do people may fuel acceptance of self-driving cars
- People more likely to trust machines than humans with their private info
- IBM donates system to Penn State to advance AI research
- ICS Seed Grants to power projects that use AI, machine learning for common good
- Penn State Berks team advances to MVP Phase of Nittany AI Challenge
- Creepy computers or people partners? Working to make AI that enhances humanity
- Sky is clearing for using AI to probe weather variability
- ‘AI will see you now’: Panel to discuss the AI revolution in health and medicine
- Privacy law scholars must address potential for nasty satellite data surprises
- Researchers take aim at hackers trying to attack high-value AI models
- Girls, economically disadvantaged less likely to get parental urging to study computers
- Seed grants awarded to projects using Twitter data
- Researchers find features that shape mechanical force during protein synthesis
- A peek at living room decor suggests how decorations vary around the world
- Interactive websites may cause antismoking messages to backfire
- Changing how government assesses risk may ease fallout from extreme financial events
- Algorithm aims to alert consumers before they use illicit online pharmacies
- Deep learning may help doctors choose better lung cancer treatments
- Using cues and actions to help people get along with artificial intelligence
- Multi-university NSF grant to boost research computing expertise